Conference PaperPDF Available

Cloud Environment for Disseminating NASS Cropland Data Layer

Authors:
Chen Zhang at George Mason University
Chen Zhang
Liping Di at George Mason University
Liping Di
Zhengwei Yang at United States Department of Agriculture
Zhengwei Yang
Li Lin
Li Lin
Li Lin
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Show all 8 authorsHide
Download full-text PDF
Read full-text
Download citation

Abstract and Figures

Cropland Data Layer (CDL) is an annual crop-specific land use map produced by the U.S. Department of Agricultural (USDA) National Agricultural Statistics Service (NASS). The CDL products are officially hosted on CropScape website which provides capabilities of geospatial data visualization, retrieval, processing, and statistics based on the open geospatial Web services. This study utilizes cloud computing technology to improve the performance of CropScape application and Web services. A cloud-based prototype of CropScape is implemented and tested. The experiment results show the performance of CropScape is significantly improved in the cloud environment. Comparing with the original system architecture of CropScape, the cloud-based architecture provides a more flexible and effective environment for the dissemination of CDL data.
Figures - uploaded by Chen Zhang
Author content
All figure content in this area was uploaded by Chen Zhang
Content may be subject to copyright.
Content uploaded by Chen Zhang
Author content
All content in this area was uploaded by Chen Zhang on Sep 06, 2019
Content may be subject to copyright.
Cloud Environment for Disseminating NASS
Cropland Data Layer
Chen Zhang†‡ , Liping Di∗† ‡, Zhengwei Yang§, Li Lin†‡, Eugene G. Yu†,
Zhiqi Yu†‡, Md. Shahinoor Rahman† ‡, Haoteng Zhao† ‡
†Center for Spatial Information Science and Systems, George Mason University, Fairfax, VA 22030, USA
‡Department of Geography and Geoinformation Sciences, George Mason University, Fairfax, VA 22030, USA
§Research and Development Division, USDA National Agricultural Statistics Service, Washington, DC 20250, USA
Email: {czhang11, ldi*}@gmu.edu, Zhengwei.Yang@nass.usda.gov, {llin2, gyu, zyu4, mrahman25, hzhao22}@gmu.edu
Abstract—Cropland Data Layer (CDL) is an annual crop-
specific land use map produced by the U.S. Department of
Agricultural (USDA) National Agricultural Statistics Service
(NASS). The CDL products are officially hosted on CropScape
website which provides capabilities of geospatial data visual-
ization, retrieval, processing, and statistics based on the open
geospatial Web services. This study utilizes cloud computing
technology to improve the performance of CropScape applica-
tion and Web services. A cloud-based prototype of CropScape
is implemented and tested. The experiment results show the
performance of CropScape is significantly improved in the cloud
environment. Comparing with the original system architecture of
CropScape, the cloud-based architecture provides a more flexible
and effective environment for the dissemination of CDL data.
Index Terms—Cloud computing, Cropland Data Layer, Cyber-
infrastructure, Interoperability, OGC Web Services
I. INTRODUCTION
As the only field-level crop planting map for the entire con-
tiguous United States (CONUS) at present, the Cropland Data
Layer (CDL) product of the U.S. Department of Agriculture
(USDA) National Agricultural Statistics Services (NASS) is
widely adopted in agro-geoinformatics. Since the first release
in 1997, the CDL products have been used to support many
agricultural applications such as land use land cover change
[1], crop area estimation [2] crop loss assessment [3], flood
mapping [4]–[7]. The national cropland maps, crop frequency
data layers, cultivated layer, and confidence layer of CDL can
be downloaded from the official website of USDA NASS [8].
However, it is a labor-intensive task for users to explore the
national-scale crop planting map using the desktop Geographic
Information Systems (GIS) software. To facilitate the use
of CDL data, CropScape, a Web-based GIS application for
agricultural geospatial data visualization and analytics, was
released by USDA NASS and Center for Spatial Information
Science and Systems of George Mason University in 2011
[9]. It provides the interactive visualization and retrieval of
all historical CDL maps as well as a variety of on-the-fly
geospatial functionalities such as crop acreage statistics and
map creation in PDF. More importantly, CropScape offers
the Open Geospatial Consortium (OGC) standards-compliant
geospatial Web services for disseminating all CDL data and
geoprocessing over the web [10]. According to the statistics of
∗corresponding author
Google Analytics, more than 208,000 users around the world
have visited and interacted with CropScape as of May 2019.
During the past decade, the volume and variety of Earth
Observation (EO) data is experiencing the explosive growth
[11]–[14]. This trend has boosted the development of advanced
computing and Cyberinfrastructure (CI) in Earth science do-
main [15]–[18]. As an important technology in CI, cloud
computing has been used to support geospatial applications
and services [19]–[22]. For example, [23] and [24] presented
the cloud-based CIs for flood monitoring and analysis, [25]
developed a Web service-based application for demographic
information modeling in the cloud. Meanwhile, the feasibility
of integrating OGC Web Services with cloud computing tech-
nology has been explored, [26] introduced a cloud environment
for processing EO data with the OGC Web Services, [27] de-
scribed a framework for implementing the Earth science model
as OGC Web Processing Service in the cloud environment.
This study aims to facilitate the dissemination of CDL data
using cloud computing technology. We immigrate the Crop-
Scape application and Web services to the cloud environment.
All data, applications, and Web services of the CropScape are
distributed as virtual machine (VM) and managed by the cloud
platform. The remainder of the paper is organized as follow.
Section II describes the high-level system architecture of
cloud-based framework for CropScape. Section III compares
the performance of CropScape Web portal and Web services in
the cloud computing environment and the current environment.
Conclusion and future works are given in the section IV.
II. SY ST EM DESIGN
The original system architecture of CropScape was de-
scribed in [9] and [28], which contains application layer,
service layer, and data layer. The application layer refers to
GIS applications and clients that support OGC Web services.
The service layer includes standard geospatial Web services
such as Web Map Service (WMS), Web Feature Service
(WFS), Web Coverage Service (WCS), and Web Processing
Service (WPS). All raster data and vector data are stored in
the data layer. As of July 2019, the CropScape data catalog
covers full volume of CDL data from 1997 to 2018, the crop
frequency layer from 2008 to 2018, the crop mask layer from
Preprint submitted to 8th International Conference on Agro-Geoinformatics (July 2019)
Fig. 1. High-level architecture of CropScape in cloud environment
2014 to 2018, U.S. boundary layers, global land cover layer,
and a few auxiliary layers.
Based on the original system architecture, we developed a
cloud-based framework to enable CropScape applications and
services in the cloud environment. Figure 1 shows the high-
level architecture of the proposed framework. Two new layers,
the Infrastructure-as-a-Service (IaaS) layer and Platform-as-a-
Service (PaaS) layer, are added to this framework. The IaaS
layer is the foundational layer of the cloud environment. It
consists of the physical cloud infrastructures, which is built
with the server cluster, and offers the computing resources
(e.g. CPU, memory, disk, bandwidth). The PaaS layer mainly
manages virtualization, operating system, middleware, and
runtime. In this study, the IaaS service and PaaS service
are offered by GeoBrain Cloud (https://cloud.csiss.gmu.edu),
a private cloud platform operated by Center for Spatial In-
formation Science and Systems of George Mason University.
The GeoBrain Cloud uses Apache CloudStack as the manage-
ment framework to manage the network, storage, computing
resources, and VMs in the server clusters.
In the proposed framework, the data layer, service layer,
and application layer could be distributed in multiple VMs.
For example, all CDL data are stored in the data VMs, all
Web services are hosted in the service VMs, the CropScape
Web portal is hosted in the application VM. Meanwhile, the
OGC standards compliant design of CropScape system makes
the framework interoperable with other GIS applications and
Web service clients.
TABLE I
EXA MPL ES O F CROPSC AP E WEB SERVICES IN CLOU D ENVIRONMENT
Web Service Operation Request Example
WMS for CONUS CDL GetMap https://cloud.csiss.gmu.edu/cdlserver/cgi-bin/wms cdlall?SERVICE=WMS&
VERSION=1.1.1&REQUEST=GetMap&LAYERS=cdl 2015&TRANSPARENT=
true&SRS=EPSG:102004&BBOX=-3987459.135,168311.354, 4472862.725,4177587.
947&FORMAT=image/png&WIDTH=800&HEIGHT=400
WCS for CONUS CDL GetCoverage https://cloud.csiss.gmu.edu/cdlserver/cgi-bin/wms cdlall?service=wcs&version=1.0.0&
request=getcapabilities
WMS for COUNS Boundary GetMap https://cloud.csiss.gmu.edu/cdlserver/cgi-bin/wms conustiger.cgi?LAYERS=conus
counties overview%2Cconus states overview&SRS=EPSG%3A102004&FORMAT=
image%2Fpng&SERVICE=WMS&VERSION=1.1.1&REQUEST=GetMap&STYLES=
&EXCEPTIONS=application%2Fvnd.ogc.se inimage&BBOX=-5228593,- 1874202.5,
5229977,5446796.5&WIDTH=300&HEIGHT=210
WFS for COUNS Boundary GetFeature https://cloud.csiss.gmu.edu/cdlserver/cgi-bin/wms conustiger.cgi?service=wfs&
version=1.1.0&request=GetFeature&typeName=conus counties&maxFeatures=100
III. EXP ER IM EN TS
A. Implementing CropScape in Cloud Environment
The cloud-based CropScape prototype Web portal can be
accessed at https://cloud.csiss.gmu.edu/CropScape. Figure 2
shows the screenshot of the CropScape Web portal in the cloud
environment. The Web service endpoint of the cloud-based
CropScape prototype is https://cloud.csiss.gmu.edu/cdlserver.
Table I lists some examples of CropScape Web services in the
cloud environment.
Fig. 2. CropScape Web portal in cloud environment.
There are few differences in both software and hardware
between the current environment and the cloud environment.
CropScape is originally deployed in two servers which han-
dling jobs sent from the CropScape Web portal and Web
services respectively. The CropScape Web portal is hosted on
the physical server with 6 cores CPU and 48GB memory.
The CropScape Web services are hosted on the server with
12 cores CPU and 32GB memory. In the cloud environment,
the CropScape instance is allocated 8 cores CPU and 16GB
memory. On the other hand, the original CropScape is running
on the Windows Server system, the PaaS service offered by
the GeoBrain Cloud is based on Linux system. Additionally,
we utilized MapServer software to serve data in the OGC Web
services and Geospatial Data Abstraction Library (GDAL) to
power geospatial functionalities. The version of these software
in two environments is different. Table II summarizes the main
specification of current environment and cloud environment.
B. Performance Test of CropScape Web Portal
To test the performance of CropScape in the cloud envi-
ronment, firstly, we compared the loading time of the portal
of prototype (https://cloud.csiss.gmu.edu/CropScape) with the
current Web portal (https://nassgeodata.gmu.edu/CropScape).
We developed a script to automatically visit the portal and
record the response time of each visit. Based on the result of
1,000 visits for each portal, the result of performance test is
illustrated as Figure 3. It can be seen from the test result that
the average response time of cloud-based prototype is 1.3s. As
a control, the average response time of the original CropScape
Web portal is 3.4s.
Fig. 3. Average response time of CropScape Web portal (lower is better).
TABLE II
SPE CIFI CATI ON OF TE ST ENVIRONMENT
Server of CropScape Web portal Server of CropScape Web services VM in cloud environment
CPU 2.1Ghz, 6 Cores 3.47Ghz, 12 Cores 2.0Ghz, 8 Cores
Memory 48GB 32GB 16GB
System Windows Server 2012 R2 Windows Server 2008 R2 Ubuntu 16.04
MapServer v6.0.3 v6.0.3 v7.0.7
GDAL v2.0.4 v1.11.1 v2.2.2
TABLE III
EXAMPLES OF CROP SCAP E WEB SE RVIC ES USE D IN PERFORMANCE TE ST
Request Cloud Environment Current Environment
CONUS
CDL
https://cloud.csiss.gmu.edu/cdlserver/cgi-bin/wms cdlall?SERVICE=
WMS&VERSION=1.1.1&REQUEST=GetMap&LAYERS=cdl
2018&TRANSPARENT=true&SRS=EPSG:102004&BBOX=
-3987459.135, 168311.354,4472862.725, 4177587.947&FORMAT=
image/png&WIDTH=2000&HEIGHT=1000
https://nassgeodata.gmu.edu/CropScapeService/wms cdlall.cgi?
SERVICE=WMS&VERSION=1.1.1&REQUEST=GetMap&
LAYERS=cdl 2018&TRANSPARENT=true&SRS=EPSG:
102004&BBOX=-3987459.135,168311.354, 4472862.725,4177587.
947&FORMAT=image/png&WIDTH=2000&HEIGHT=1000
State
CDL
https://cloud.csiss.gmu.edu/cdlserver/cgi-bin/wms cdl ia?SERVICE=
WMS&VERSION=1.1.1&REQUEST=GetMap&LAYERS=cdl
2018 ia&STYLES=&SRS=EPSG:4326&BBOX=-97,40.2, -90, 43.7&
WIDTH=2000&HEIGHT=1000&FORMAT=image/png
https://nassgeodata.gmu.edu/CropScapeService/wms cdl ia.cgi?
SERVICE=WMS&VERSION=1.1.1&REQUEST=GetMap&
LAYERS=cdl 2018 ia&STYLES=&SRS=EPSG:4326&BBOX=
-97, 40.2,- 90,43.7&WIDTH=2000&HEIGHT=1000&FORMAT=
image/png
Fig. 4. Average response time of Web Map Service for 2018 CONUS CDL
(lower is better).
C. Performance Test of CropScape Web Services
The second experiment tested the performance of CDL Web
services. We compared the response time of WMS requests
in the cloud environment and current environment. Table III
shows the examples of the WMS requests for the CONUS
CDL and state-level CDL. Figure 4 and Figure 5 illustrates
the average response time for loading 2018 CONUS CDL map
and 2018 CDL map of Iowa state respectively.
IV. CONCLUSION AND FUTURE WOR KS
This study utilized the cloud computing technology to
facilitate the disseminating CDL data. Based on the current
system architecture, we added the PaaS layer and IaaS layer to
enable the cloud-based framework for CropScape application
Fig. 5. Average response time of Web Map Service for 2018 CDL of Iowa
state (lower is better).
and its Web services. The experiment result shows the average
response time of CropScape Web portal in the cloud environ-
ment is much lower than in the current server. Meanwhile,
the performance of CropScape Web Service is significantly
improved in the cloud environment.
Currently, the WMS, WCS, and WFS of CropScape has
been implemented in the GeoBrain Cloud. The cloud-based
WPS of CropScape is still under development. The prototype
of cloud-based CropScape described in the experiment section
is based on the single VM. The performance of the current
implementation would be affected while the service is over-
loaded. This issue could be solved by distributing multiple
instances in the cloud and dynamically allocating computing
resources to the application and Web services. In the future,
we will investigate the scalability of the proposed architecture
and test the performance in real use case.
ACK NOW LE DG EM EN T
This study is supported by USDA NASS.
REFERENCES
[1] T. J. Lark, R. M. Mueller, D. M. Johnson, and H. K. Gibbs, “Mea-
suring land-use and land-cover change using the U.S. department of
agriculture’s cropland data layer: Cautions and recommendations,” In-
ternational Journal of Applied Earth Observation and Geoinformation,
vol. 62, pp. 224–235, Oct. 2017.
[2] X.-P. Song, P. V. Potapov, A. Krylov, L. King, C. M. Di Bella,
A. Hudson, A. Khan, B. Adusei, S. V. Stehman, and M. C. Hansen,
“National-scale soybean mapping and area estimation in the United
States using medium resolution satellite imagery and field survey,”
Remote Sensing of Environment, vol. 190, pp. 383–395, Mar. 2017.
[3] M. S. Rahman, L. Di, E. Yu, L. Lin, C. Zhang, and J. Tang, “Rapid
Flood Progress Monitoring in Cropland with NASA SMAP,” Remote
Sensing, vol. 11, no. 2, p. 191, Jan. 2019.
[4] L. Lin, L. Di, E. G. Yu, L. Kang, R. Shrestha, M. S. Rahman, J. Tang,
M. Deng, Z. Sun, C. Zhang, and L. Hu, “A review of remote sensing
in flood assessment,” in 2016 5th International Conference on Agro-
Geoinformatics, 2016.
[5] M. S. Rahman, L. Di, R. Shrestha, E. G. Yu, L. Lin, C. Zhang, L. Hu,
J. Tang, and Z. Yang, “Agriculture flood mapping with Soil Moisture
Active Passive (SMAP) data: A case of 2016 Louisiana flood,” in 2017
6th International Conference on Agro-Geoinformatics, Aug. 2017, pp.
1–6.
[6] L. Lin, L. Di, J. Tang, E. Yu, C. Zhang, M. S. Rahman, R. Shrestha, and
L. Kang, “Improvement and Validation of NASA/MODIS NRT Global
Flood Mapping,” Remote Sensing, vol. 11, no. 2, p. 205, Jan. 2019.
[7] R. Shrestha, L. Di, E. G. Yu, L. Kang, Y. Shao, and Y. Bai, “Regression
model to estimate flood impact on corn yield using MODIS NDVI and
USDA cropland data layer,” Journal of Integrative Agriculture, vol. 16,
no. 2, pp. 398–407, Feb. 2017.
[8] USDA NASS Research and Science, “Cropland Data Layer Releases,”
https://www.nass.usda.gov/Research and Science/Cropland/Release/,
2019.
[9] W. Han, Z. Yang, L. Di, and R. Mueller, “CropScape: A Web service
based application for exploring and disseminating US conterminous
geospatial cropland data products for decision support,” Computers and
Electronics in Agriculture, vol. 84, pp. 111–123, 2012.
[10] W. Han, L. Di, and Z. Yang, “Developing geoprocessing service for
Cropland Data Layer thematic map creation,” in 2013 Second Interna-
tional Conference on Agro-Geoinformatics (Agro-Geoinformatics), Aug.
2013, pp. 572–576.
[11] S. Nativi, P. Mazzetti, M. Santoro, F. Papeschi, M. Craglia, and
O. Ochiai, “Big Data challenges in building the Global Earth Observa-
tion System of Systems,” Environmental Modelling & Software, vol. 68,
pp. 1–26, Jun. 2015.
[12] M. Chi, A. Plaza, J. A. Benediktsson, Z. Sun, J. Shen, and Y. Zhu, “Big
Data for Remote Sensing: Challenges and Opportunities,” Proceedings
of the IEEE, vol. 104, no. 11, pp. 2207–2219, Nov. 2016.
[13] L. Di, “Big data and its applications in agro-geoinformatics,” in
2016 IEEE International Geoscience and Remote Sensing Symposium
(IGARSS), Jul. 2016, pp. 189–191.
[14] A. Karmas, A. Tzotsos, and K. Karantzalos, “Geospatial Big Data for
Environmental and Agricultural Applications,” in Big Data Concepts,
Theories, and Applications, S. Yu and S. Guo, Eds. Cham: Springer
International Publishing, 2016, pp. 353–390.
[15] J. L. Schnase, T. J. Lee, C. A. Mattmann, C. S. Lynnes, L. Cinquini,
P. M. Ramirez, A. F. Hart, D. N. Williams, D. Waliser, P. Rinsland, W. P.
Webster, D. Q. Duffy, M. A. McInerney, G. S. Tamkin, G. L. Potter,
and L. Carriere, “Big Data Challenges in Climate Science: Improving
the next-generation cyberinfrastructure,” IEEE Geoscience and Remote
Sensing Magazine, vol. 4, no. 3, pp. 10–22, Sep. 2016.
[16] L. Di, Z. Sun, and C. Zhang, “Facilitating the Easy Use of Earth
Observation Data in Earth System Models through CyberConnector,”
in AGU Fall Meeting Abstracts, 2017.
[17] Z. Sun, L. Di, H. Hao, X. Wu, D. Q. Tong, C. Zhang, C. Virgei, H. Fang,
E. Yu, X. Tan, P. Yue, and L. Lin, “CyberConnector: A service-oriented
system for automatically tailoring multisource Earth observation data to
feed Earth science models,” Earth Science Informatics, vol. 11, no. 1,
pp. 1–17, Mar. 2018.
[18] S. Wang and M. F. Goodchild, “CyberGIS for Transforming Geospatial
Discovery and Innovation,” in CyberGIS for Geospatial Discovery and
Innovation, ser. GeoJournal Library, S. Wang and M. F. Goodchild, Eds.
Dordrecht: Springer Netherlands, 2019, pp. 3–10.
[19] P. Yue, H. Zhou, J. Gong, and L. Hu, “Geoprocessing in Cloud
Computing platforms – a comparative analysis,” International Journal
of Digital Earth, vol. 6, no. 4, pp. 404–425, Jul. 2013.
[20] K. Evangelidis, K. Ntouros, S. Makridis, and C. Papatheodorou,
“Geospatial services in the Cloud,” Computers & Geosciences, vol. 63,
pp. 116–122, Feb. 2014.
[21] Z. Li, C. Yang, Q. Huang, K. Liu, M. Sun, and J. Xia, “Building
Model as a Service to support geosciences,” Computers, Environment
and Urban Systems, vol. 61, pp. 141–152, Jan. 2017.
[22] C. Yang, Q. Huang, Z. Li, K. Liu, and F. Hu, “Big Data and cloud com-
puting: Innovation opportunities and challenges,” International Journal
of Digital Earth, vol. 10, no. 1, pp. 13–53, 2017.
[23] Z. Wan, Y. Hong, S. Khan, J. Gourley, Z. Flamig, D. Kirschbaum,
and G. Tang, “A cloud-based global flood disaster community cyber-
infrastructure: Development and demonstration,” Environmental Mod-
elling & Software, vol. 58, pp. 86–94, Aug. 2014.
[24] M. M. Morsy, J. L. Goodall, G. L. O’Neil, J. M. Sadler, D. Voce,
G. Hassan, and C. Huxley, “A cloud-based flood warning system for
forecasting impacts to transportation infrastructure systems,” Environ-
mental Modelling & Software, vol. 107, pp. 231–244, Sep. 2018.
[25] L. Lin, L. Di, C. Zhang, L. Hu, J. Tang, and E. G. Yu, “Developing
a Web Service Based Application for Demographic Information Mod-
eling and Analyzing,” in 2017 6th International Conference on Agro-
Geoinformatics, 2017, pp. 14–18.
[26] C. Zhang, L. Di, Z. Sun, E. G. Yu, L. Hu, L. Lin, J. Tang, and M. S.
Rahman, “Integrating OGC Web Processing Service with cloud comput-
ing environment for Earth Observation data,” in 2017 6th International
Conference on Agro-Geoinformatics, 2017.
[27] C. Zhang, L. Di, Z. Sun, L. Lin, E. G. Yu, and J. Gaigalas, “Exploring
cloud-based Web Processing Service: A case study on the implementa-
tion of CMAQ as a Service,” Environmental Modelling & Software, vol.
113, pp. 29–41, Mar. 2019.
[28] W. Han, Z. Yang, L. Di, B. Zhang, and C. Peng, “Enhancing Agricultural
Geospatial Data Dissemination and Applications Using Geospatial Web
Services,” IEEE Journal of Selected Topics in Applied Earth Observa-
tions and Remote Sensing, vol. 7, no. 11, pp. 4539–4547, Nov. 2014.
... The transfer learning technique is extremely useful when there are fewer labels [134]. Research has indicated that the combination of machine learning, remote sensing, and GIS has promising potential to outperform many traditional field surveys and standalone remote sensing classification methods [100,151,152]. ...
... Obsolete Field surveys and investigations [85]; evaluation of culture and history [24,157] Both methodologies and results are easy to understand [24,157,158] Require knowledgeful investigators [58,85]; high financial cost; labor-intensive and low scalability [8,151] Conventional Statistical correlation models [11,58,88,91,96,97,[153][154][155]160]; transfer learning [134][135][136][137][138][140][141][142][143]161,162] Models are easy to use and replicable [97,167,168]; low financial cost [85] Too many algorithms [96][97][98]; results are not reliable [96,153] Novel Machine learning imagery classification [95,99,[120][121][122]181,184,185]; time-series deep learning [87,183,190,191] Emerging technology and promising results [95,185]; low financial cost [85] Require high quality labels [172,192] and advancing algorithms [99]; lack of research [182] ...
... Traditional poverty mapping is not only labor-intensive but also poses a tremendous financial burden [58,151]. Studies have summarized traditional poverty mapping approaches in various regions around the world. ...
Remote Sensing of Urban Poverty and Gentrification
Article
Full-text available
  • Oct 2021
In the past few decades, most urban areas in the world have been facing the pressure of an increasing population living in poverty. A recent study has shown that up to 80% of the population of some cities in Africa fall under the poverty line. Other studies have shown that poverty is one of the main contributors to residents’ poor health and social conflict. Reducing the number of people living in poverty and improving their living conditions have become some of the main tasks for many nations and international organizations. On the other hand, urban gentrification has been taking place in the poor neighborhoods of all major cities in the world. Although gentrification can reduce the poverty rate and increase the GDP and tax revenue of cities and potentially bring opportunities for poor communities, it displaces the original residents of the neighborhoods, negatively impacting their living and access to social services. In order to support the sustainable development of cities and communities and improve residents’ welfare, it is essential to identify the location, scale, and dynamics of urban poverty and gentrification, and remote sensing can play a key role in this. This paper reviews, summarizes, and evaluates state-of-the-art approaches for identifying and mapping urban poverty and gentrification with remote sensing, GIS, and machine learning techniques. It also discusses the pros and cons of remote sensing approaches in comparison with traditional approaches. With remote sensing approaches, both spatial and temporal resolutions for the identification of poverty and gentrification have been dramatically increased, while the economic cost is significantly reduced.
View
... The CDL covers the entire USA at 30 m spatial resolution from 2008 to the present, downloaded through CropScape [37,38] and providing over 140 land use classes. The accuracy of major crop types in most areas is near 95% [39]. ...
End-to-End Predictive Network for Accurate Early Crop Planting Area Estimation
Article
Full-text available
  • May 2025
Early crop planting area estimation is crucial for achieving effective government resource allocation, optimizing resource distribution planning, and preparation related to food security. Utilizing remote sensing images during the crop growth period for crop planting area estimation has garnered increasing attention. However, area estimation from remote sensing often lags in obtaining image data. Moreover, this method is also influenced by the quality of remote sensing image data and segmentation accuracy. This paper proposes a new method for early area estimation based on multi-year land cover data using a three-dimensional convolutional end-to-end network. This method eliminates the impact of the intermediate process of image segmentation accuracy on area estimation. Additionally, multi-subimage technology is employed to solve the issue of inconsistent input sample size, and label distribution smoothing technology is used to tackle the problem of unbalanced sample distribution. The proposed method was evaluated on U.S. corn and soybean datasets. In comparison to baseline methods, the method achieved relative errors of 0.67% for corn and 3.72% for soybeans at the national level in the United States in 2021. This demonstrates the effectiveness of the proposed method and the potential for early decision-making support. This approach offers a new perspective for area estimation, significantly advancing the timing of planting area prediction and enhancing the accuracy of early area estimation, providing actionable insights for decision-making and resource management.
View
... Given the importance of soil water content in irrigation scheduling, the improvement of online soil moisture data accessibility [46][47][48][49][50][51][52] could enhance greatly the development of more effective scheduling methods. With precise estimation of real-time soil moisture [53] and well-defined threshold, as well as weather forecast data, agricultural soilcrop-atmosphere system modeling might achieve an evolution over conventional process-based model. ...
View
... CropScape [19] was developed to visualize, disseminate, and analyze the annually updated Cropland Data Layer (CDL), which contains crop-and other specific land cover classifications for the conterminous United States. A cloud environment is built for serving CDL products to provide geo-referenced, high-accuracy, 30 or 56 m resolution, crop-specific land cover information since 1997 [36]. This web application provides great convenience for different users to access, view, and analyze the product. ...
WaterSmart-GIS: A Web Application of a Data Assimilation Model to Support Irrigation Research and Decision Making
Article
Full-text available
Irrigation is the primary consumer of freshwater by humans and accounts for over 70% of all annual water use. However, due to the shortage of open critical information in agriculture such as soil, precipitation, and crop status, farmers heavily rely on empirical knowledge to schedule irrigation and tend to excessive irrigation to ensure crop yields. This paper presents WaterSmart-GIS, a web-based geographic information system (GIS), to collect and disseminate near-real-time information critical for irrigation scheduling, such as soil moisture, evapotranspiration, precipitation, and humidity, to stakeholders. The disseminated datasets include both numerical model results of reanalysis and forecasting from HRLDAS (High-Resolution Land Data Assimilation System), and the remote sensing datasets from NASA SMAP (Soil Moisture Active Passive) and MODIS (Moderate-Resolution Imaging Spectroradiometer). The system aims to quickly and easily create a smart, customized irrigation scheduler for individual fields to relieve the burden on farmers and to significantly reduce wasted water, energy, and equipment due to excessive irrigation. The system is prototyped here with an application in Nebraska, demonstrating its ability to collect and deliver information to end-users via the web application, which provides online analytic functionality such as point-based query, spatial statistics, and timeseries query. Systems such as this will play a critical role in the next few decades to sustain agriculture, which faces great challenges from climate change and increased natural disasters.
View
... The IaaS, PaaS, and SaaS services are powered by a private cloud platform operated by Center for Spatial Information Science and Systems of George Mason University, GeoBrain Cloud (https://cloud.csiss.gmu.edu). This cloud platform provides the computing resources to operational data service systems [16], Earth observation data processing workflows [17], [18], and Earth system science models [19]. ...
An Overview of Agriculture Cyberinformatics Tools to Support USDA NASS Decision Making
Conference Paper
Full-text available
  • Jul 2021
Cyberinformatics tools have been extensively applied to aid decision support in agriculture. This paper presents an overview of cyberinformatics tools to support decision making for the National Agricultural Statistics Service (NASS) of the U.S. Department of Agriculture (USDA). We review three web-based applications: CropScape, VegScape, and Crop-CASMA. Specifically, we summarize the data products of the three tools, including Cropland Data Layer (CDL) products, vegetation index products based on Moderate Resolution Imaging Spectrora-diometer (MODIS) data, and soil moisture products derived from the Soil Moisture Active Passive (SMAP) data. Also, we compare the geoprocessing capability and web service support of these tools. Meanwhile, two use cases and applications are presented to demonstrate the capability of supporting USDA NASS decision making with the cyberinformatics tools.
View
... All CDL products can be accessed through CropScape (https://nassgeodata.gmu.edu/ CropScape), a web-based geospatial information system developed and maintained by the Center for Spatial Information Science and Systems of George Mason University (Han et al., 2012;Zhang et al., 2019b). ...
Rapid in-season mapping of corn and soybeans using machine-learned trusted pixels from Cropland Data Layer
Article
Full-text available
  • Oct 2021
  • INT J APPL EARTH OBS
A timely and detailed crop-specific land cover map can support many agricultural applications and decision makings. However, in-season crop mapping over a large area is still challenging due to the insufficiency of ground truth in the early stage of a growing season. To address this issue, this paper presents an efficient machine-learning workflow for the rapid in-season mapping of corn and soybeans fields without ground truth data for the current year. We use trusted pixels, a set of pixels that are predicted from the historical Cropland Data Layer (CDL) data with high confidence in the current year’s crop type, to label training samples on multi-temporal satellite images for crop type classification. The entire mapping process only involves a limited number of satellite images acquired within the growing season (normally 3–4 images per scene) and no field data needs to be collected. According to the investigation on 12 states of the U.S. Corn Belt, it is found that a considerable number of trusted pixels can be identified from the historical CDL data by the trusted pixel prediction model based on artificial neural network. According to the experiment on 49 Landsat-8 scenes and 31 Sentinel-2 tiles, the in-season maps of corn and soybeans are expected to reach 85%–95% agreement with CDL as well as field data by mid-July. Once the in-season satellite imagery becomes available, the crop cover map can be rapidly created even with limited computational resources. This study provides a new perspective and detailed guidance for rapid in-season mapping of corn and soybeans, which can be potentially applied to identify more diverse crop types and scaled up to the entire United States.
View
View
View
Preseason Crop Type Prediction Using Crop Sequence Boundaries
Article
Full-text available
  • Mar 2023
  • COMPUT ELECTRON AGR
A field-level model for pre-season crop type prediction is introduced. • Fields are referred to crop sequence boundaries and are derived from historical NASS Cropland Data Layers. • Field-based predictions are competitive with previous pixel-based forecasting models when compared to Farm Service Agency ground-reference data. • Summaries by crop sequence boundaries provide a computational efficient procedure for large CDL datasets. Abstract Preseason crop-type prediction has emerged as a valuable tool for agricultural use. A reliable algorithm for early crop-type prediction has many applications , including crop mapping, planted acreage prediction, crop yield prediction, disaster response, area sample design, crop survey imputation, and more. The primary source of data for preseason crop prediction in the United States is the United States Department of Agriculture National Agricultural Statistics Service's Cropland Data Layer, which is an annual crop specific land cover data set produced using satellite imagery and administrative data. Historical crop rotations taken from the Cropland Data Layer can be used by machine learning models to predict the future crop type in any given land area. The dataset obtained from the Cropland Data Layer is large, containing hundreds of millions of pixels per state. Current approaches for predictive modeling have utilized sampling, resulting in more scalable machine learning. In this paper, the authors propose an alternative method that uses all available Cropland Data Layer data in a rapid and memory-efficient manner. The proposed method relies on a novel technique for identifying groups of pixels with homogenous cropping history. These pixel groups are summarized as polygons representing field boundaries, referred to as crop sequence boundaries. Use of these new polygons for modeling significantly reduces the computational burden of incorporating all the Cropland Data Layer data and eliminates any increased uncertainty brought on by sampling. This novel polygon-based approach competes well with existing methods in scalability and accuracy, achieving the highest overall accuracy in 23 out of 24 tests performed.
View
Validation and refinement of cropland data layer using a spatial-temporal decision tree algorithm
Article
Full-text available
  • Mar 2022
Space-based crop identification and acreage estimation have played a significant role in agricultural studies in recent years, due to the development of Remote Sensing technology. The Cropland Data Layer (CDL), which was developed by the U.S. Department of Agriculture (USDA), has been widely used in agricultural studies and achieved massive success in recent years. Although the CDL’s accuracy assessments report high overall accuracy on various crops classifications, misclassification is still common and easy to discern from visual inspection. This study is aimed to identify and resolve inaccurate crop classification in CDL. A decision tree method was employed to find questionable pixels and refine them with spatial and temporal crop information. The refined data was then evaluated with high-resolution satellite images and official acreage estimates from USDA. Two validation experiments were also developed to examine the data at both the pixel and county level. Data generated from this research was published online in two repositories, while both applications allow users to download the entire dataset at no cost.
View
Rapid flood progress monitoring in cropland with NASA SMAP
Article
Full-text available
  • Jan 2019
Research in different agricultural sectors, including in crop loss estimation during flood and yield estimation, substantially rely on inundation information. Spaceborne remote sensing has widely been used in the mapping and monitoring of floods. However, the inability of optical remote sensing to cloud penetration and the scarcity of fine temporal resolution SAR data hinder the application of flood mapping in many cases. Soil Moisture Active Passive (SMAP) level 4 products, which are model-driven soil moisture data derived from SMAP observations and are available at 3-h intervals, can offer an intermediate but effective solution. This study maps flood progress in croplands by incorporating SMAP surface soil moisture, soil physical properties, and national floodplain information. Soil moisture above the effective soil porosity is a direct indication of soil saturation. Soil moisture also increases considerably during a flood event. Therefore, this approach took into account three conditions to map the flooded pixels: a minimum of 0.05 m3m−3 increment in soil moisture from pre-flood to post-flood condition, soil moisture above the effective soil porosity, and the holding of saturation condition for the 72 consecutive hours. Results indicated that the SMAP-derived maps were able to successfully map most of the flooded areas in the reference maps in the majority of the cases, though with some degree of overestimation (due to the coarse spatial resolution of SMAP). Finally, the inundated croplands are extracted from saturated areas by Spatial Hazard Zone areas (SHFA) of Federal Emergency Management Agency (FEMA) and cropland data layer (CDL). The flood maps extracted from SMAP data are validated with FEMA-declared affected counties as well as with flood maps from other sources.
View
Improvement and validation of NASA/MODIS NRT global flood mapping
Article
Full-text available
  • Jan 2019
The remote-sensing based Flood Crop Loss Assessment Service System (RF-CLASS) is a web service based system developed and managed by the Center for Spatial Information Science and Systems (CSISS). The system uses Moderate Resolution Imaging Spectroradiometer (MODIS)-based flood data, which was implemented by the Dartmouth Flood Observatory (DFO), to provide an estimation of crop loss from floods. However, due to the spectral similarity between water and shadow, a noticeable amount of false classification of shadow can be found in the DFO flood products. Traditional methods can be utilized to remove cloud shadow and part of mountain shadow. This paper aims to develop an algorithm to filter out noise from permanent mountain shadow in the flood layer. The result indicates that mountain shadow was significantly removed by using the proposed approach. In addition, the gold standard test indicated a small number of actual water surfaces were misidentified by the proposed algorithm. Furthermore, experiments also suggest that increasing the spatial resolution of the slope helped reduce more noise in mountains. The proposed algorithm achieved acceptable overall accuracy (>80%) in all different filters and higher overall accuracies were observed when using lower slope filters. This research is one of the very first discussions on identifying false flood classification from terrain shadow by using the highly efficient method.
View
Exploring cloud-based Web Processing Service: A case study on the implementation of CMAQ as a Service
Article
Full-text available
  • Mar 2019
  • ENVIRON MODELL SOFTW
As an important tool for air quality simulation, the Community Multiscale Air Quality (CMAQ) model is widely used in the environmental modeling community. However, setting up and running the CMAQ model could be challenging for many scientists, especially when they have limited computing resources and little experience in handling large-scale input data. In this study, we explore the cloud-based Web Processing Service (WPS) and present the Cloud WPS framework to support implementing Earth science model as WPS. Specifically, to make CMAQ easier to use for scientists through the latest standard-based Web service technology, CMAQ-WS, a prototype of CMAQ as a Service, is developed and tested. The result of the experiment shows the framework significantly improves not only the performance of but also ease of use of the CMAQ model thus providing great benefits to the environmental modeling community. Meanwhile, the proposed framework provides a general solution to integrate Earth science model, WPS, and cloud infrastructure, which can greatly reduce the workload of Earth scientists.
View
A Cloud-Based Flood Warning System for Forecasting Impacts to Transportation Infrastructure Systems
Article
Full-text available
  • May 2018
  • ENVIRON MODELL SOFTW
The ability to quickly and accurately forecast flooding is increasingly important as extreme weather events become more common. This work focuses on designing a cloud-based real-time modeling system for supporting decision makers in assessing flood risk. The system, built using Amazon Web Services (AWS), automates access and pre-processing of forecast data, execution of a computationally expensive and high-resolution 2D hydrodynamic model, Two-dimensional Unsteady Flow (TUFLOW), and map-based visualization of model outputs. A graphical processing unit (GPU) version of TUFLOW was used, resulting in an 80x execution time speed-up compared to the central processing unit (CPU) version. The system is designed to run automatically to produce near real-time results and consume minimal computational resources until triggered by an extreme weather event. The system is demonstrated for a case study in the coastal plain of Virginia to forecast flooding vulnerability of transportation infrastructure during extreme weather events.
View
Agriculture flood mapping with Soil Moisture Active Passive (SMAP) data: A case of 2016 Louisiana flood
Conference Paper
Full-text available
  • Aug 2017
Abstract: Agriculture is one of the most affected sectors by the flood. Spaceborn remote sensing is widely used for flood mapping and monitoring in recent decades. Some applications such as flood crop loss assessment require data with fine temporal resolution to monitor short-lived flood. MODIS is providing remote sensing data with 1-2 days temporal resolution which has frequently been used for flood mapping for a large area. However, incapability to penetrate through the cloud hindered the application of optical remote sensing in flood mapping in many cases. Thus, radar remote sensing especially synthetic aperture radar (SAR) already shows the capability for the flood mapping in cloud condition. However, monitoring of short-lived flood is not possible using freely available SAR data because of the long revisit capacity of these SAR systems. Therefore, microwave remote sensing with fine temporal resolution might be helpful for flood inundation mapping. Soil Moisture Active Passive (SMAP) is a microwave remote sensing initiative which is providing 3-hourly soil moisture data. Therefore, this study tries to map agriculture flood based on SMAP soil moisture data and soil physical properties. Soil moisture above the filed capacity might be the indication of soil inundation. Moreover, It has been observed that there is an increment in soil moisture during the flood. Therefore, this approach considered three conditions to map the flooded pixel: a minimum of 0.05 increment in soil moisture, a soil moisture threshold 0.40 (moisture above the field capacity) and the 72 consecutive hours. To avoid the random increment in soil moisture a 3-day moving window is applied to the time series data. The flood map extracted from SMAP data is validated with FEMA declared inundated cropland. The overall accuracy is 60% and about 32% of commission error. The overestimation of the flood by SMAP data due to the coarse spatial resolution (9km) of SMAP data.
View
Integrating OGC Web Processing Service with cloud computing environment for Earth Observation data
Conference Paper
Full-text available
  • Aug 2017
Statistics show the volume of Earth Observation (EO) data increases in the exponential level during the past decade. As the new generation computing platform to meet the big data challenge, cloud computing significantly facilitates the large-scale EO data processing depending on its powerful computing capability. In this paper, we propose a Cloud WPS architecture integrating the cloud computing environment and OGC Web Services. Based on the architecture, we implement the GeoBrain Cloud, an Apache Cloudstack based private cloud computing platform with a series of state-of-the-art open-source libraries and software. The result suggests that Web Processing Services and cloud computing environment could be successfully integrated based on the proposed architecture.
View
View
CyberConnector: a service-oriented system for automatically tailoring multisource Earth observation data to feed Earth science models
Article
Full-text available
  • Mar 2018
Feeding multisource Earth observation (EO) data into Earth science models (ESM) remains a daunting challenge. This paper presents a service-oriented approach as an alternative solution. It uses geospatial web services to process the EO data and geoprocessing workflow for automation. Different from existing approaches, it takes advantage of virtual data products (VDP) to release modelers from intensive data processing. It can directly connect ESMs to public EO sources via Cyberinfrastructure. A prototype called CyberConnector is implemented. CyberConnector supports intuitive building of VDP, automatic execution of workflows and effortless retrieval of model-ready input files. We used it to stream multiple datasets to several ESMs including finite-volume coastal ocean model (FVCOM) and cloud-resolving model (CRM). The results show that CyberConnector can truly benefit modelers on time saving and effort minimizing.
View
Measuring land-use and land-cover change using the U.S. department of agriculture’s cropland data layer: Cautions and recommendations
Article
Full-text available
  • Oct 2017
Monitoring agricultural land is important for understanding and managing food production, environmental conservation efforts, and climate change. The United States Department of Agriculture's Cropland Data Layer (CDL), an annual satellite imagery-derived land cover map, has been increasingly used for this application since complete coverage of the conterminous United States became available in 2008. However, the CDL is designed and produced with the intent of mapping annual land cover rather than tracking changes over time, and as a result certain precautions are needed in multi-year change analyses to minimize error and misapplication. We highlight scenarios that require special considerations, suggest solutions to key challenges, and propose a set of recommended good practices and general guidelines for CDL-based land change estimation. We also characterize a problematic issue of crop area underestimation bias within the CDL that needs to be accounted for and corrected when calculating changes to crop and cropland areas. When used appropriately and in conjunction with related information, the CDL is a valuable and effective tool for detecting diverse trends in agriculture. By explicitly discussing the methods and techniques for post-classification measurement of land-cover and land-use change using the CDL, we aim to further stimulate the discourse and continued development of suitable methodologies. Recommendations generated here are intended specifically for the CDL but may be broadly applicable to additional remotely-sensed land cover datasets including the National Land Cover Database (NLCD), Moderate Resolution Imaging Spectroradiometer (MODIS)-based land cover products, and other regional, national, and global land cover classification maps.
View
CyberGIS for Transforming Geospatial Discovery and Innovation
Chapter
  • Jan 2019
Geographic information science and systems (GIS) have undergone rapid growth during the past several decades. This growing trend seems likely to persist into the foreseeable future driven by numerous diverse applications and enabled by steady progress of related technologies. As a geospatial data deluge permeates broad scientific and societal realms, to sustain the trend, however, requires GIS to be innovated based on synergistic integration of data-intensive and spatial approaches enabled by advanced cyberinfrastructure—a rapidly evolving infrastructure of communication, computing, and information technologies. Consequently, cyberGIS has been developed as a fundamentally new cyberinfrastructure and GIS modality comprising a seamless blending of advanced cyberinfrastructure, GIS, and spatial analysis and modeling capabilities and, thus, has enabled scientific advances and shown broad societal impacts while contributing to the advancement of cyberinfrastructure. For example, the U.S. National Science Foundation (NSF) has funded a major multi-institution initiative on cyberGIS software integration for sustained geospatial innovation—arguably the largest investment by NSF on related subjects during the past several years. Therefore, this book represents a timely effort to inform pertinent research communities about opportunities and challenges, roadmaps for research and development, and major progress, trends, and impacts of cyberGIS. The book serves as an authoritative source of information to fill the void of introducing this new, exciting, and growing field.
View