Liping Di

George Mason University | GMU · Center for Spatial Information Science and Systems

Mapping nationwide in-season crop-type data is a significant and challenging task in agriculture remote sensing. The existing data product for U.S. crop-type planting, such as the Cropland Data Layer (CDL), falls short in facilitating near-real-time applications. This paper designed a workflow aimed at automating the generation of in-season CDL-lik...

This study presents a streamlined, automated classification method to map land-cover type Local Climate Zones (LCZs). Using a two-phase hybrid approach, we first generated training samples through universal decision rules and subsequently, a Machine Learning (ML) algorithm was trained on the generated samples to classify LCZs. The proposed model ha...

Sugarcane is a significant crop in terms of annual biomass in the world. Timely and accurate mapping of sugarcane planting is important for food security and sustainability. However, accurately remote-sensing-based mapping sugarcane remains challenging due to two reasons: (1) the scarcity of sugarcane training samples, and (2) the diverse sugarcane...

Given the increasing prevalence of droughts, unpredictable rainfall patterns, and limited access to dependable water sources in the United States and worldwide, it has become crucial to implement effective irrigation scheduling strategies. Irrigation is triggered when some variables, such as soil moisture or accumulated water deficit, exceed a give...

This chapter briefly covers the five core dimensions of remote sensing big data, that is, volume, variety, velocity, veracity, and value. There are also other Vs to be explored, like Visualization for effectively high-dimensional visuals and exploration (Huang et al. J Integrat Agric 17:1915–1931, 2018), Volatility for data time-sensitivity (Antune...

This chapter covers computing platforms that are fit for remote sensing big data computing. The evolution of the geospatial computing environment is briefly reviewed, that is, stand-alone, centralized, and distributed. The high-performance computing environment is also briefly reviewed, that is, supercomputer, grid computing, and cloud computing. S...

The chapter review major big data initiatives that have a geospatial component of remote sensing and Earth Observations. These include initiatives in selected countries and international organizations. The reviews highlighted that geospatial standards play an important role in these initiatives to support interoperation of data, metadata, and servi...

This chapter defines the basic concepts of big data analytic platforms. Big data analytic platforms can be classified by different criteria. There are a variety of infrastructures for big analytics platforms, including a peer-to-peer system, clusters, high-performance computers, grid computing, and cloud computing. There are several options for sto...

This chapter reviews major standards that are fit for remote sensing big data. Two groups of standards are reviewed: metadata standards and data standards. The International Organization for Standardization (ISO) standards are discussed as the major standard efforts in enabling storing, managing and transporting of remote sensing data. The Open Geo...

Remote sensing big data management covers aspects of governance, curation, organization, administration, and dissemination—data discovery (both collection and granule levels) and access. This chapter first discusses different aspects of remote sensing big data governance, which blueprint standards and policy. Secondly, remote sensing data curation...

An algorithm is evaluated primarily in two metrics—temporal and spatial complexity. This chapter presents algorithm design challenges for remote sensing big data from the five dimensions—Volume, Velocity, Variety, Veracity, and Value. Volume requires algorithm design to consider processing performance, modularity, data sparsity, dimensionality, fea...

This chapter focuses on strategies to extend and adapt traditional machine learning algorithms for remote sensing and geospatial big data. Ten major strategies are discussed. They are distributed and parallel learning, data reduction and approximate computing, feature selection and feature extraction, incremental learning, deep learning, ensemble a...

The Chapter introduces major Remote Sensing Big Data Collection Challenges—5Vs (Volume, Variety, Velocity, Veracity, and Value) and other remote-sensing-data-collection-specific challenges: identification, storage, distribution, representation, fusion, and visualization. Cyberinfrastructure is introduced as one of the platforms to enable the collec...

Two examples of big data management systems for remote sensing are presented in this chapter. They are CWIC (CEOS (Committee on Earth Observation Satellites) WGISS (the Working Group on Information Systems and Services) Integrated Catalog) and GCI (GEOSS (Global Earth Observation System of Systems) Common Infrastructure). Both are international eff...

This chapter covers the life cycle of using remote sensing big data in real-world actions. The application life cycle includes three stages: modeling, prediction, and decision making. The modeling stage processes remote sensing data and produces information. The prediction stage extrapolates and forecasts the phenomena information through time seri...

This chapter demonstrated one experiment of constructing long time series of land cover maps using temporal segment modeling method. The long time series involves many different types of data and large volume of data. The mining of temporal patterns using all the accumulated Earth Observations makes it possible to build long time series of land cov...

The chapter introduces basic concepts of remote sensing. Major remote sensors are reviewed by radiometric spectrum and by work mode. One focus of the review is data generation rate and the contribution of different sensors to remote sensing big data. By radiometric spectrums, there are multi- and hyperspectral remote sensing, active microwave remot...

This chapter discusses challenges and opportunities in remote sensing big data. Three challenges are discussed. They are data complexity, data quality, and infrastructure change. The growth of remote sensing big data also introduces several new opportunities. The discussed changes are single scale to multiscale, on-premise servers to distributed se...

This chapter describes data fusion, a common task for remote sensing big data analytics that produces improved images by fusing data with different (spatial, spectral, radiometric, and temporal) resolutions. One newly developed, learning-based spatiotemporal fusion model, the Deep Convolutional Spatiotemporal Fusion Network (DCSTFN), is described a...

This chapter covers concepts of big data analytics in general, including definitions, categories, and use case overview. Processes and requirements for remote sensing big data analytics are discussed. Two standard efforts on big data analytics are briefly covered, that is, ISO (International Organization for Standardization) Big Data Working Group...

This chapter describes an example of processing remote sensing big data in a distributed computing environment for realizing the agricultural drought monitoring and forecasting system. The system demonstrated the event-based processing workflow using a service-oriented architecture. Standards of geospatial Web services are adopted to achieve reusab...

This study developed a rapid rice yield estimation workflow and customized yield prediction model by integrating remote sensing and meteorological data with machine learning (ML). Several issues need to be addressed while developing a crop yield estimation model, including data quality issues, data processing issues, selecting a suitable machine le...

Mapping rice area is a critical resource planning task in many South Asia countries where rice is the primary crop. Remote sensing-based methods typically rely on domain knowledge, such as crop calendar and crop phenology, and supervised classification with ground truth samples. Applying such methods on Google Earth Engine (GEE) has been proven eff...

Changes in land surface temperature (LST) affect human society and the natural environment, especially for agricultural activities. In recent decades, satellite remote sensing has been used as an alternative approach to ground observation sites for monitoring LST. Prior research has offered broad insights into global and continental-level Land Surf...

This study develops a general method to evaluate the contributions of localized urbanization and global climate change to long-term urban land surface temperature (ULST) change. The method is based on the understanding that long-term annual ULST is controlled by three factors: (1) localized urbanization, (2) global climate change, and (3) interannu...

This paper describes a set of Near-Real-Time (NRT) Vegetation Index (VI) data products for the Conterminous United States (CONUS) based on Moderate Resolution Imaging Spectroradiometer (MODIS) data from Land, Atmosphere Near-real-time Capability for EOS (LANCE), an openly accessible NASA NRT Earth observation data repository. The data set offers a...

Soil moisture is an essential parameter to understand crop conditions throughout the growing season. Collecting soil moisture data by field observation is labor-intensive, especially when attempting to obtain Conterminous United States (CONUS) geographic coverage. In addition, using soil moisture for assessing current and future crop conditions is...

CONTEXT Mapping crop types from satellite images is a promising application in agricultural systems. However, it is a challenge to automate in-season crop type mapping over a large area because of the insufficiency of ground truth and issues of scalability, reusability, and accessibility of the classification model. This study introduces a framewor...

Large–area crop type identification and mapping for cropland are intensively crucial for agriculture research, yield forecast, and disaster management. The United States Department of Agriculture (USDA) produces the Cropland Data Layer (CDL) for Contiguous United States cropland that involves crop type spatial distribution with 30m resolution. Howe...

Sundarbans, a UNESCO World Heritage site, is the world's largest mangrove forest covers an area of about 3,900 sq. mi, of which forests in Bangladesh extend over 2,323 sq. mi and in India, they extend over 1,640 sq. mi. The Sundarbans is called the shelter of Bangladesh as it protects southern coastal regions from natural disasters such as Cyclones...

Lagos, Nigeria, is considered a rapidly growing urban hub. This study focuses on an urban development characterization with remote sensing-based variables for Lagos as well as understanding spatio-temporal precipitation responses to the changing intensity of urban development. Initially, a harmonic analysis showed an increase in yearly precipitatio...

Currently Lyme disease (LD) is the most common vector-borne disease in the United States. Understanding the potential effects of urban expansion on LD risk is an emerging global health concern. The U.S. Northeastern corridor has experienced a spatio-temporal increase in Lyme disease (LD) and rapid urban expansion over the past decades. The effects...

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 study aims to develop a general method and evaluate the contributions of localized urbanization and global climate change to long-term urban land surface temperature (ULST) change. Combined daytime and nighttime daily MODIS products were used to fill data biases from satellite-observed data and applied to tropical regions during dry season fro...

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...

Evapotranspiration (ET) is an important parameter for crop growth monitoring and land surface modeling. This paper proposed a new workflow, namely ESVEP-RF, to calculate ET during the crop growing season using MODIS data by combining the advantages of the trapezoidal model and Random Forest (RF) algorithm. In ESVEP-RF, the endmember-based soil and...

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...

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...

Assessing the performance of land change simulation models is a critical step when predicting the future landscape scenario. The study was conducted in the district of Varanasi, Uttar Pradesh, India because the city being "the oldest living city in the world" attracts a vast population to reside here for short and long-term, leaving the city's ecos...

Drought is one of the billion-dollar natural disasters and hard to trace and measure. In recent years drought monitoring becomes much easier with remote sensing. However, it is still difficult to pin vegetation variances on drought because of the delay of the caused vegetation stress. To assess vegetative drought, it is important to first understan...

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-...

Sentinel-2 images have been widely used in studying land surface phenomena and processes, but they inevitably suffer from cloud contamination. To solve this critical optical data availability issue, it is ideal to fuse Sentinel-1 and Sentinel-2 images to create fused, cloud-free Sentinel-2-like images for facilitating land surface applications. In...

This chapter summarized state-of-the-art data sources and sourcing methods of agro-geoinformatics. The data mainly comes from four sources: satellite, airborne, and in-situ sensors, and human reports. Overall, the satellite datasets have the best spatial and temporal coverages. The airborne and in-situ datasets are mostly project-specific or site-s...

Urban studies concern the evolution of spatial structure in cities, where information is often tied to location. The discovery of information is in a high-dimensional space based on spatial and temporal dimensions, where the spatial relationships of components play roles in studying urban evolution. Spatial search in urban studies has to deal with...

With the rapid development of sensor and data technologies, the volume of agricultural-related Earth observation data has been expanded exponentially. Meanwhile, these data are tremendously diverse in terms of the format, sensor, heterogeneity, and quality. Geospatial Web service technologies have shown great potential to build the infrastructure f...

Agro-geoinformatics deals with collecting, managing, and analyzing agricultural-related geospatial data, which are domain-specific big data. This chapter discusses the general characteristics of big data, the specific features of agro-geoinformatics and agro-big data, and the examples of agro-geoinformatics projects dealing with big agro-big data....

Agro-geoinformation, the agricultural-related geo-information, is the key information in the agricultural decision making and policy formulation process. Agro-geoinformatics is the interdisciplinary field of study on acquisition, processing, management, and applications of agro-geoinformation. This book summarizes the recent progresses of the agro-...

This paper proposed a geoscience model service integrated workflow-based rainstorm waterlogging analysis method to overcome the defects of conventional waterlogging analysis systems. In this research, we studied a general OGC WPS service invoking strategy, an automatic asynchronous invoking mechanism of WPS services in the BPEL workflow, and a dist...

Existing Hadoop-based remote sensing data processing approaches are insufficient for efficiently meeting the requirements of applications, especially when large remote sensing datasets are involved. This paper proposes an adaptive Spark-based remote sensing data processing method on the cloud that achieves improved efficiency and stability. The met...

To effectively disseminate location-linked information despite the existence of digital walls across institutions, this study developed a cross-institution mobile App, named GeoFairy2, to overcome the virtual gaps among multi-source datasets and aid the general users to make thorough accurate in-situ decisions. The app provides a one-stop service w...

In general, low density airborne LiDAR (Light Detection and Ranging) data are typically used to obtain the average height of forest trees. If the data could be used to obtain the tree height at the single tree level, it would greatly extend the usage of the data. Since the tree top position is often missed by the low density LiDAR pulse point, the...

Accurate crop-specific damage assessment immediately after flood events is crucial for grain pricing, food policy, and agricultural trade. The main goal of this research is to estimate the crop-specific damage that occurs immediately after flood events by using a newly developed Disaster Vegetation Damage Index (DVDI). By incorporating the DVDI alo...

Complexities of virus genotypes and the stochastic contacts in human society create a big challenge for estimating the potential risks of exposure to a widely spreading virus such as COVID-19. To increase public awareness of exposure risks in daily activities, we propose a birthday-paradox-based probability model to implement in a web-based system,...

The leaf area index (LAI) is an essential indicator used in crop growth monitoring. In the study, a hybrid inversion method, which combined a physical model with a statistical method, was proposed to estimate the crop LAI. The simulated compact high-resolution imaging spectrometer (CHRIS) canopy spectral crop reflectance datasets were generated usi...

Accurate and timely estimation of crop yield at a small scale is of great significance to food security and harvest management. Recent studies have proven remote sensing is an efficient method for yield estimation and machine learning, especially deep learning, can infer a good prediction by integrating multi-source datasets like satellite data, cl...