Ram C. Sharma’s research while affiliated with Tokyo University of Information Sciences and other places

Japan Aerospace Exploration Agency (JAXA) is going to launch Advanced Land Observing Satellite 3 (ALOS-3) after 2022. ALOS-3 satellite is capable of observing global land areas with wide swath (4000 km along-track direction and 70 km cross-track direction) at high spatial resolution (panchromatic: 0.8m, multispectral: 3.2m). Maintenance and updating of land cover and vegetation information at national level is one of the major goals of the ALOS-3 mission. This paper presents the potential of simulated ALOS-3 images for the classification and mapping of land cover and vegetation types at Genus-Physiognomy-Ecosystem (GPE) level. We acquired and simulated WorldView-3 images according to the configuration of the ALOS-3 satellite sensor and the simulated ALOS-3 images were utilized for the classification and mapping of land cover and vegetation types in three sites (Hakkoda, Zao, and Shiranuka) in northern Japan. This research dealt with 17 land cover and vegetation types in Hakkoda site, 25 land cover and vegetation types in Zao site, and 12 land cover and vegetation types in Shiranuka site. Ground truth data were newly collected in three sites, and we employed eXtreme Gradient Boosting (XGBoost) classifier with the implementation of 10-fold cross-validation method for assessing the potential of ALOS-3S images. The classification accuracies obtained in Hakkoda, Zao, and Shiranuka sites in terms of f1-score were 0.810, 0.729, and 0.805 respectively. The fine scale (3.2m) land cover and vegetation maps produced in the study sites showed clear and detailed view of the distribution of plant communities. Regardless of the limited number of the temporal images, ALOS-3S images showed high potential (at least 0.729 F1-score) for the land cover and vegetation classification in all three sites. The availability of more cloud free temporal scenes is expected for improved classification and mapping in the future.

Classification and mapping of plant communities is an essential step for conservation and management of ecosystems and biodiversity. We adopt the Genus-Physiognomy-Ecosystem (GPE) system developed in the previous study for satellite-based classification of plant communities at a broad scale. This paper assesses the potential of multi-spectral and multi-temporal images collected by Sentinel-2 satellites for the classification and mapping of GPE types. This research was conducted in seven representative study sites in different climatic regions ranging from one warm-temperate site in Aya to six cool-temperate sites in Hakkoda, Zao, Oze, Shirakami, Kitakami and Shiranuka. The GPE types were enumerated in all study sites and ground truth data were collected with reference to extant vegetation surveys, visual interpretation of high-resolution images, and onsite field observations. We acquired all Sentinel-2 Level-1C product images available for the study sites between 2017-2019 and generated monthly median composite images consisting of ten spectral and twelve spectral-indices. The Gradient Boosting Decision Trees (GBDT) classifier was employed for the supervised classification of the satellite data with the support of ground truth data. The cross-validation accuracy in terms of kappa coefficient varied from 87% in Oze site with 41 GPE types to 95% in Hakkoda site with 19 GPE types; with average performance of 91% across all sites. The GPE maps produced in this research demonstrated a clear distribution of plant communities in all seven sites, highlighting the potential of Sentinel-2 multi-spectral and multi-temporal images with GPE classification system for operational and broad-scale mapping of plant communities.

This research introduces Genus-Physiognomy-Ecosystem (GPE) mapping at a prefecture level through machine learning of multi-spectral and multi-temporal satellite images at 10m spatial resolution, and later integration of prefecture wise maps into country scale for dealing with 88 GPE types to be classified from a large size of training data involved in the research effectively. This research was made possible by harnessing entire archives of Level-2A product, Bottom of Atmosphere reflectance images collected by MultiSpectral Instruments onboard a constellation of two polar-orbiting Sentinel-2 mission satellites. The satellite images were pre-processed for cloud masking and monthly median composite images consisting of 10 multi-spectral bands and 7 spectral indexes were generated. The ground truth labels were extracted from extant vegetation survey maps by implementing systematic stratified sampling approach and noisy labels were dropped out for preparing a reliable ground truth database. Graphics Processing Unit (GPU) implementation of Gradient Boosting Decision Trees (GBDT) classifier was employed for classification of 88 GPE types from 204 satellite features. The classification accuracy computed with 25% test data varied from 65-81% in terms of F1-score across 48 prefectural regions. This research produced seamless maps of 88 GPE types first time at a country scale with an average 72% F1-score. In addition, mapping of solar panels and vegetation disturbance are added.

This research introduces Genus-Physiognomy-Ecosystem (GPE) mapping at a prefecture level through machine learning of multi-spectral and multi-temporal satellite images at 10m spatial resolution, and later integration of prefecture wise maps into country scale for dealing with 88 GPE types to be classified from a large size of training data involved in the research effectively. This research was made possible by harnessing entire archives of Level-2A product, Bottom of Atmosphere reflectance images collected by MultiSpectral Instruments onboard a constellation of two polar-orbiting Sentinel-2 mission satellites. The satellite images were pre-processed for cloud masking and monthly median composite images consisting of 10 multi-spectral bands and 7 spectral indexes were generated. The ground truth labels were extracted from extant vegetation survey maps by implementing systematic stratified sampling approach and noisy labels were dropped out for preparing a reliable ground truth database. Graphics Processing Unit (GPU) implementation of Gradient Boosting Decision Trees (GBDT) classifier was employed for classification of 88 GPE types from 204 satellite features. The classification accuracy computed with 25% test data varied from 65-81% in terms of F1-score across 48 prefectural regions. This research produced seamless maps of 88 GPE types first time at a country scale with an average 72% F1-score.

Advanced Land Observing Satellite 3 (ALOS-3) is capable of observing global land areas with wide swath (4000 km along-track direction and 70 km cross-track direction) at high spatial resolution (panchromatic: 0.8m, multispectral: 3.2m). Maintenance and updating of Land Cover and Vegetation (LCV) information at national level is one of the major goals of the ALOS-3 mission. This paper presents the potential of simulated ALOS-3 images for the classification and mapping of LCV types. We simulated WorldView-3 images according to the configuration of the ALOS-3 satellite sensor and the ALOS-3 simulated (ALOS-3S) images were utilized for the classification and mapping of LCV types in two cool temperate ecosystems. This research dealt with classification and mapping of 17 classes in the Hakkoda site and 25 classes in the Zao site. We employed a Gradient Boosted Decision Tree (GBDT) classifier with 10-fold cross-validation method for assessing the potential of ALOS-3S images. In the Hakkoda site, we obtained overall accuracy, 0.811 and kappa coefficient, 0.798. In the Zao site, overall accuracy and kappa coefficient were 0.725 and 0.711 respectively. Regardless of limited temporal scenes available in the research, ALOS-3S images showed high potential (at least 0.711 kappa-coefficient) for the LCV classification. The availability of more temporal scenes from ALOS-3 satellite is expected for improved classification and mapping of LCV types in the future.

Classification and mapping of plant communities is an essential step for conservation and management of ecosystems and biodiversity. We adopt the Genus-Physiognomy-Ecosystem (GPE) system developed in previous study for satellite-based classification of plant communities. This paper assesses the potential of multi-spectral and multi-temporal images collected by Sentinel-2 satellites. This research was conducted in five representative study sites in a temperate region. It consists of 44 types of plant communities including a few land cover types as well. The plant community types were enumerated in the study sites and ground truth data were prepared with reference to extant vegetation surveys, visual interpretation of high-resolution images, and onsite field observations. We acquired all Sentinel-2 Level-1C product images available for the study sites between 2017-2019 and generated monthly median composite images consisting of ten spectral and twelve spectral-indices. Gradient Boosting Decision Trees (GBDT) classifier was employed as an efficient and distributed gradient boosting technique for the supervised classification of big datasets involved in the research. The cross-validation accuracy in terms of kappa coefficient varied from 87% in Oze site with 41 land cover and plant community types to 95% in Hakkoda site with 19 land cover and plant community types; with average performance of 91% across all sites. In addition, the resulting maps demonstrated a clear distribution of plant community types involved in all sites, highlighting the potential of Sentinel-2 multi-spectral and multi-temporal images with GPE classification system for operational and broad-scale mapping of land cover and plant communities.

Utilization of the Bidirectional Reflectance Distribution Function (BRDF) model parameters obtained from the multi-angular remote sensing is one of the approaches for the retrieval of vegetation structural information. In this research, the potential of multi-angular vegetation indices, formulated by the combination of multi-spectral reflectance from different view angles, for the retrieval of forest above-ground biomass was assessed in the New England region. The multi-angular vegetation indices were generated by the simulation of the Moderate Resolution Imaging Spectroradiometer (MODIS) BRDF/Albedo Model Parameters Product (MCD43A1 Version 6)-based BRDF parameters. The effects of the seasonal (spring, summer, autumn, and winter) composites of the multi-angular vegetation indices on the above-ground biomass, the angular relationship of the spectral reflectance with above-ground biomass, and the interrelationships between the multi-angular vegetation indices were analyzed. Among the existing multi-angular vegetation indices, only the Nadir BRDF-adjusted NDVI and Hot-spot incorporated NDVI showed significant relationship (more than 50%) with the above-ground biomass. The Vegetation Structure Index (VSI), newly proposed in the research, performed in the most efficient way and explained 64% variation of the above-ground biomass, suggesting that the right choice of the spectral channel and observation geometry should be considered for improving the estimates of the above-ground biomass. In addition, the right choice of seasonal data (summer) was found to be important for estimating the forest biomass, while other seasonal data were either insensitive or pointless. The promising results shown by the VSI suggest that it could be an appropriate candidate for monitoring vegetation structure from the multi-angular satellite remote sensing.

Vegetation mapping and monitoring is important as the composition and distribution of vegetation has been greatly influenced by land use change and the interaction of land use change and climate change. The purpose of vegetation mapping is to discover the extent and distribution of plant communities within a geographical area of interest. The paper introduces the Genus-Physiognomy-Ecosystem (GPE) system for the organization of plant communities from the perspective of satellite remote sensing. It was conceived for broadscale operational vegetation mapping by organizing plant communities according to shared genus and physiognomy/ecosystem inferences, and it offers an intermediate level between the physiognomy/ecosystem and dominant species for the organization of plant communities. A machine learning and cross-validation approach was employed by utilizing multi-temporal Landsat 8 satellite images on a regional scale for the classification of plant communities at three hierarchical levels: (i) physiognomy, (ii) GPE, and (iii) dominant species. The classification at the dominant species level showed many misclassifications and undermined its application for broadscale operational mapping, whereas the GPE system was able to lessen the complexities associated with the dominant species level classification while still being capable of distinguishing a wider variety of plant communities. The GPE system therefore provides an easy-to-understand approach for the operational mapping of plant communities, particularly on a broad scale.

Vegetation indices are commonly used techniques for the retrieval of biophysical and chemical attributes of vegetation. This paper presents the potential of an Autoencoders (AEs) and Convolutional Autoencoders (CAEs)-based self-supervised learning approach for the decorrelation and dimensionality reduction of high-dimensional vegetation indices derived from satellite observations. This research was implemented in Mt. Zao and its base in northeast Japan with a cool temperate climate by collecting the ground truth points belonging to 16 vegetation types (including some non-vegetation classes) in 2018. Monthly median composites of 16 vegetation indices were generated by processing all Sentinel-2 scenes available for the study area from 2017 to 2019. The performance of AEs and CAEs-based compressed images for the clustering and visualization of vegetation types was quantitatively assessed by computing the bootstrap resampling-based confidence interval. The AEs and CAEs-based compressed images with three features showed around 4% and 9% improvements in the confidence intervals respectively over the classical method. CAEs using convolutional neural networks showed better feature extraction and dimensionality reduction capacity than the AEs. The class-wise performance analysis also showed the superiority of the CAEs. This research highlights the potential of AEs and CAEs for attaining a fine clustering and visualization of vegetation types.