Net ecosystem productivity (NEP) is a key indicator that reflects the net absorption or net emissions of carbon in terrestrial ecosystems to measure the carbon sink capacity of vegetation. This paper builds machine learning models such as Random Forest Regression model (RFR), Support Vector Regression machine model (SVR) and Back Propagation Neural Network model (BPNN), coupled with Fluxnet2015 data set and NDVI data to build machine learning training data set. Based on different machine learning models, centrally learning the characteristics of the training data set and mining the implicit relationship information between each impact factor and NEP. The estimation results of each machine learning model are evaluated through R2, RMSE and other accuracy indicators and analyze the importance of the characteristics that affect NEP prediction. Provide scientific basis and technical support for ecological environmental monitoring and protection. The research results show that the Random Forest Regression model (RFR) and the Support Vector Regression machine model (SVR) have good prediction results for NEP data, and R2 is greater than 0.7. NDVI is an important influence parameter for the overall prediction of NEP of vegetation types. When predicting NEP data of different vegetation types, the prediction results of the Random Forest Regression model (RFR) and the Support Vector Regression machine model (SVR) are generally good. Except for permanent wetland, all other types of R2 are greater than 0.6, and the Back Propagation Neural Network model's NEP prediction results for permanent wetland are better than the Random Forest Regression model and the Support Vector Regression machine model. These three machine models can well predict the NEP of mixed forests, and the accuracy of the prediction results of permanent wetland NEP is poor compared with other types. The accuracy of the prediction results of the Support Vector Regression machine model for woody savannas is better than that of the other two machine learning models. NDVI and latent heat flux have an important impact on the NEP prediction of various vegetation types. Characteristics such as soil water content, sensible heat flux and net radiation are one of the key influencing factors in the NEP prediction of specific vegetation types. Research shows that NEP estimation based on machine learning and multisource data can provide remote sensing monitoring results of carbon revenue and expenditure in terrestrial ecosystems similar to real observation on the ground, and can provide scientific basis and technical support for the formulation of ecological and environmental protection policies and ecological environmental monitoring and protection.
This study developed the first 10-meter resolution Hawaiian Cropland Data Layers (HCDL) for 2023 using gap-filled Sentinel-Landsat multi-sensor 10-day composites and advanced algorithms. Evaluating both Random Forest and CNN models, the research found Random Forest to be more effective for operational purposes, achieving an average accuracy of 93.6%. The HCDL provides a critical tool for Hawaii's agricultural management, bridging data gaps and supporting informed decision-making.
Climate risk profile studies play a vital role in Africa, considering the continent’s unique vulnerability to climate change. With diverse ecosystems, economies, and social contexts, Africa faces a multitude of climate-related risks, including extreme weather events, water scarcity, agricultural disruptions. Understanding and assessing these risks through climate risk profile studies is crucial for effective adaptation and mitigation planning. Our study aimed to construct seasonal crop risk profiles utilizing a composite index methodology, analyzing historical climate data spanning the past three decades. This composite index integrates spatially explicit evaluations of heat stress, drought stress, and flood hazards. Specifically focused on agricultural risks, our study further refines these hazards concerning crops during the growing seasons. Furthermore, our analysis will assess changes and trends in the frequency and severity of these hazards over time. These investigations offer invaluable insights into the precise climate threats confronting African nations and regions, empowering policymakers and communities to make well-informed decisions regarding resource allocation, infrastructure development, and socioeconomic planning.
FAO with the support of the Government of The Netherlands maintain a publicly accessible near real time database called WaPOR (https://wapor.apps.fao.org). The information provided enables a range of services for farmers, irrigation operators and government agencies to better monitor and promote the efficient use of natural resources. To translate the data into actionable and policy relevant information, remote sensing, hydrology and agronomy experts are developing tools and applications in selected countries. In Tunisia, for example, data from WaPOR is being used to support agricultural advisory services delivered through a smartphone application. WaPOR Actual EvapoTranspiration ETa data from Jendouba area is used in the IREY app developed by the Institut National des Grandes Cultures (INGC). The Smart Irrigation App IREY provides advices to farmers on real-time irrigation schedules for selected crops.
The land use change of Linyi City from 2010 to 2020 was analyzed based on RS technology, Using Landsat8 remote sensing images as the data source and ENVI remote sensing image processing software, the images were preprocessed and supervised for classification, and the land use types in Linyi City were divided into five categories. Using comparative analysis method to compare the land use changes in Linyi City in 2010, 2015, and 2020, and quantitatively analyze the relevant land use changes using transfer matrix and degree model of land use. By using remote sensing to analyze land use status, we can better understand the distribution of land resources in the study area. This not only provides basic research data for the planning and management of land resources nationwide, but also has important significance for promoting urbanization construction and economic development in Linyi City.
Soil organic matter (SOM) serves as a crucial indicator for assessing soil fertility and cultivated land quality. This study developed a SOM prediction method based on a back propagation neural network with genetic algorithm variable selection. The experimental area was in Hailun City, a typical black soil region of Heilongjiang Province, China. A total of 157 sampling points were selected at a depth of 0-20 cm. The Landsat 8 OLI images from the bare soil period were used for calculating the spectral indexes. The Shuttle Radar Topography Mission (SRTM) data was utilized to extract topographic factors. Then the multiple stepwise regression (MSR) and genetic algorithm (GA) methods were used to screen the variables as input, respectively. Multiple linear regression (MLR) and back propagation neural network (BPNN) methods were utilized to build the SOM prediction model. The root mean square error (RMSE) and correlation coefficient (R2) were employed to evaluate the accuracy of SOM prediction. Finally, the optimal model was used to predict the SOM in the black soil area. The results indicated that the GA outperformed MSR in variable selection. The BP neural network (with GA-selected variables GA_BP) has the highest accuracy for the SOM prediction, with an R2 of 0.94 and an RMSE of 0.14, followed by the BP neural network with a stepwise regression-selected factor (MSR_BP) with an R2 of 0.91 and an RMSE of 0.24. The R2 of BPNN was 0.84 and the RMSE was 0.29, while MSR showed the lowest accuracy, with an R2 of 0.69 and an RMSE of 0.57. This study not only proved the advantages of GA in significantly improving model accuracy by decreasing the dimensionality of the inputsbut also provided effective methods for improving the precision of SOM remote sensing prediction, showing potential applications in predicting SOM in black soil areas.
The most recent 1-km soil moisture (SM) product from the Soil Moisture Active Passive (SMAP) mission provides unprecedented insights into global SM variability. However, the narrow swath and low revisit schedule of the sensors create significant data gaps in the daily product. The reduced spatial coverage obstructs its application for hydrological or agricultural studies that require continuous time series observations. In this study, we investigate the use of an Empirical Orthogonal Function (EOF) based algorithm to reconstruct missing observations in the soil moisture dataset. The reconstruction method is tested with the SMAP-derived 1km daily soil moisture product in the Continental United States. The accuracy of the reconstructed values is assessed by comparing them with in situ measurements.
This study consists of desk research under the scope of the FAO Hand-in-Hand Initiative (HiHI), an evidence-based, country-led, and country-owned initiative of the Food and Agriculture Organization of the United Nations (FAO) targeting to accelerate agricultural transformation and sustainable rural development with the goal of eradicating poverty, ending hunger and malnutrition, and reducing inequalities. The research follows the Initiative objective to use integrated geospatial analysis and market-oriented agri-food systems lens to differentiate territories and focus action, to identify opportunities to raise the incomes, reduce the inequities and vulnerabilities of rural populations. The analysis deliver suitability assessments aimed at value chain infrastructure interventions for around 60 participating countries, designed for, crops, livestock (dairy/meat), and fish farming. Research methodology include literature review on region, country, and value chain/sector, for background and context, with the suitability modelling adopting geographic Information system (GIS) Multi-criteria Evaluation (MCE) approach using weighted factors, converting, and combining geospatial data and decision criteria. Spatial decision problems involve a set of alternatives and multiple (sometimes opposing) assessment criteria, frequently evaluated by many intervenient. In GIS-MCE, GIS capabilities are enhanced by multi-criteria decision analysis procedures, techniques, and algorithms for structuring decision problems, to design, evaluate and prioritize alternatives. Based on specific theory, geospatial modelling is developed for each farming system within a value chain, playing with criteria combination and weighting, and combining different set of constraints. The business rules define sub-models, the criteria, and spatial constraints, that characterize the socioeconomic (supply, demand, and infrastructure /accessibility) and biophysical factors, that are considered to define a locations suitability. Transportation network infrastructures are modelled as raster-based travel time/cost analysis, and the accessibility to market (demand) is processed for large urban areas, utilizing population size and purchase power as weighting factors. Final recommendation, mapping outputs, on site location, utilizes exclusive criteria or constraints, e.g. distance to major roads, access to information and communication technologies, access to finance. GIS-MCE provides a replicable and auditable model, improving communication between project participants and decision-makers, offering different perspectives on problem solution, and helping to redefine initial specification or criteria. It usually follows a three-stage hierarchy of: intelligence, design, and choice. In the intelligence phase, data are acquired, processed, and exploratory data analysis is performed. The design phase entails the formal modelling and development of a solution set of spatial decision alternatives. The choice phase involves selecting location alternatives using specific decision rules, used to evaluate and rank alternatives. From a critical standpoint it can be stated that, while quantitative data analysis and evidence gathering through GIS modelling can contribute to attaining evidence for decision-making processes, a set of complex socio-economic, political, cultural, ethno-anthropological aspects, and power relations, shape decision-making processes. Modelling is also as good as the input data, quality and reliability support the extent to which conclusions can be trusted, and specification and objectives define modelling assumptions and approximations and can always produce distinct answers.
Rift Valley fever (RVF) is a vector-borne disease that significantly impacts livelihoods, trade, tourism, and human health. Currently endemic in Africa and parts of the Near East, RVF primarily affects sheep, goats, cattle, buffaloes, and camels. Outbreaks are closely linked to climate anomalies like heavy rains and flooding, which create favorable conditions for mosquito populations, increasing disease risk. Early warning systems are essential to prevent RVF outbreaks. The Food and Agriculture Organization of the United Nations (FAO) developed a web-based RVF Early Warning Decision Support Tool (RVF DST), integrating near real-time risk maps, historical disease data, and expert eco-epidemiological knowledge. Launched in 2019 and integrated into FAO’s geospatial platform in 2020, the RVF DST was piloted in Kenya, Uganda, and United Republic of Tanzania. It provides near real-time risk maps updated weekly, covering the entire African continent. The tool uses a Multi-Criteria Decision Analysis approach to create real-time risk maps for RVF introduction, spread, and occurrence. It has improved FAO’s ability to identify high-risk areas, issue early warnings, incite members to step up preparedness and prevent RVF outbreaks, with alerts sent 2-3 months before the first signs of infection. These alerts, combined with surveillance activities and expert knowledge, help validate potential hotspots and support early response efforts. The RVF DST has enhanced vigilance and preparedness in Eastern Africa and fostered collaboration between FAO, national veterinary services, and partners like the World Health Organization (WHO), Intergovernmental Authority on Development (IGAD), and World Organisation for Animal Health (WOAH). It demonstrates the value of near real-time risk modelling and digital innovation in improving disease preparedness and response, setting a standard for global health security.
Water quality holds most important in aquatic environments, particularly within the context of reservoirs located in Hainan Island, where its availability is limited yet its benefits are profoundly significant. The assessment of water quality in such regions is imperative for comprehending ecosystem health and ensuring the sustainable management of water resources. High-resolution satellites equipped with Multispectral Instruments (MSI), such as Sentinel-2, offer a promising avenue for monitoring water quality through atmospheric correction and water quality modeling techniques. In the domain of water quality assessment, the selection of atmospheric correction (AC) and water quality parameter (WQP) models plays a pivotal role in determining the accuracy of results. This variability underscores the importance of choosing appropriate models to precisely estimate parameters such as suspended particle matter (SPM) and chlorophyll a (Chl a). To delve deeper into this aspect, Sentinel-2/MSI images underwent processing utilizing three different AC models: POLYMER, ACOLITE, and C2RCC. Subsequently, two different WQP models were applied: OCX for Chl a and Nechad for SPM. Upon analysis, the results revealed notable discrepancies based on the combinations of AC and WQP models employed. The Polymer-Nechad demonstrated lower errors across four metrics, with an RMSE of 19.14, RMSLE of 0.50, MAPE of 72.5%, Bias of 1.21, and MAE of 2.54. Specifically, the POLYMER-OCX and C2RCC-OCX combination exhibited superior performance in estimating Chl a concentration, while the POLYMER-Nechad combination yielded the most accurate estimations for SPM. Moreover, this study contributes to the advancement of long-time series remote sensing techniques for reservoir (Daguangba) monitoring in Hainan Island. The study also presents a detailed analysis of the annual changes in Chl a and SPM concentrations in the Daguangba Reservoir from 2016 to 2023, highlighting the potential of Sentinel-2/MSI data for long-term environmental monitoring. The year-to-year analysis from 2016 to 2023 depicted a fluctuating trend in both parameters, with the highest values recorded in 2017. Following this peak, a general decreasing trend in Chl a was observed, with a temporary rise in 2020, possibly due to specific environmental events or changes in the ecosystem. The implications of these findings extend beyond academic research, with practical applications in environmental management and resource conservation.In conclusion, this study highlights the importance of remote sensing technology in assessing water quality parameters and emphasizes the potential benefits of employing Sentinel-2/MSI data for effective environmental monitoring and management in reservoir located in Hainan Island. The integration of advanced remote sensing techniques holds promise for enhancing our ability to monitor and safeguard aquatic ecosystems for future generations.
Located in Yunnan Province, the “Three Parallel Rivers region “ is a renowned tourist resort and World Natural Heritage site. It boasts the distinction of being the world’s most extensive geological and geomorphological museum, an invaluable repository for biological genes, and a natural alpine garden. With its significant vertical gradient and diverse environmental sensitive zones, this region exhibits relatively shallow soil depth, making it a focal point for research on sustainable development of regional ecosystems. In order to comprehensively assess the ecosystem development in the “Three Parallel Rivers region,” this study employs bibliometric analysis to examine 3918 papers published domestically and internationally over a span of 30 years. The analysis encompasses paper quantity, sources, citation frequencies, primary authors, research institutions, and research hotspots. The findings indicate that: (1) Since 2000, the Three Parallel Rivers region has garnered increasing societal attention, leading to a rapid surge in research publications on this topic, with an average annual output of 122 papers. Notably, Chinese researchers have contributed the most papers; however, there is room for further improvement in terms of paper quality.(2)The study of the three parallel rivers has been primarily advanced by prominent scholars such as He Daming, Sha Yucang, Li Yimin, and their colleagues. Collaborative efforts between research institutions including the Institute of Geographical Sciences and Natural Resources Research of the Chinese Academy of Sciences, the University of the Chinese Academy of Sciences, Yunnan University, and others have played a crucial role. However, there is limited collaboration among relevant scholars and research institutions with minimal communication or cooperation between different units and teams domestically or internationally.(3) The research primarily focuses on the resources, energy, and geology of the Three Parallel Rivers region, with a specific emphasis on three key research areas: water conservation and hydropower, topography and geomorphology, and bioecology. In order to enhance the international influence of our research findings in this area, it is crucial to prioritize originality and breakthrough contributions. Additionally, we should foster diverse collaborations among different research institutions and disciplines while promoting theoretical innovation alongside practical applications. These efforts will inject new momentum into Three Parallel Rivers region studies. It is anticipated that this paper will serve as a valuable reference for expanding both the breadth and depth of future research in this region.
In northern China, wheat is the primary staple crop, cultivated extensively in arid and semiarid regions where drought poses a significant challenge to production. Understanding wheat’s response to drought stress and its recovery mechanisms is crucial for ensuring future yield stability. To address this, we have conducted a field experiment manipulating rainfall on spring wheat in the semi-arid rain-fed agricultural area of the Loess Plateau in China. We induced drought stress at various growth stages of spring wheat by completely excluding rainfall using rain-out shelters. We measured and compared several eco-physical characteristics of wheat growth, including height, chlorophyll content, chlorophyll fluorescence parameters, biomass, and grain yield. The results showed that normal growth and development of spring wheat could be obviously influenced by continuous water stress given at vegetative stages. Drought stress can shorten the growth period of spring wheat. Specifically, during periods of drought, the heading and flowering stages are delayed the earlier the drought occurs, while the maturation stage advances. If the drought persists during the grain filling stage without recovery in precipitation, it significantly reduces the thousand-grain weight, consequently leading to decreased yield. Additionally, the ongoing drought process resulted in a decrease in leaf moisture, chlorophyll content, and chlorophyll fluorescence. Dry matter accumulation rate in the organ allocation of plants, pre-reproductive concentrated in the leaves, late reproduction concentrated in the panicle, and stem throughout dry matter accumulation rate decreased. These changes in plant physiology and allocation of resources lead to considerable differences in plant morphology, particularly in terms of plant height. After the natural precipitation was restored, the leaf water, chlorophyll content, and chlorophyll fluorescence rapidly returned to normal levels, and the morphological changes did not recover significantly under severe stress. The experimental data collected from two seasons strongly indicates that chlorophyll fluorescence parameters can identify crop water stress. The study highlights the ability of plants to function during drought and recover immediately after rehydration during the vegetative growth period is important in determining the final yield of wheat. Chlorophyll fluorescence parameters can identify crop water stress. We believe that this work lays the foundation for research on crop drought-related mechanisms and provide opportunities for the management of high-yield crop production.
Hazelnuts are a vital agricultural commodity, contributing significantly to global food systems and public health due to their nutritional value and economic importance as an export crop. Turkiye is a leading global producer of hazelnuts as a major source of income and a strategic agricultural product. In this study, we selected two regions named Acmabasi and Parali from Sakarya province which ranks third in the production of hazelnut among Turkish provinces and utilized very high-resolution (VHR) aerial photographs to classify hazelnut fields. In addition to the standard CORINE Land Cover (LC) classes, we defined a specific hazelnut class, verified through field observations. Various machine learning-based classification algorithms, including Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), and Bayesian classification, were employed with object-based classification with different feature values. The performance of the models was evaluated using overall accuracy and F1-score metrics and the best results are obtained with Support Vector Machines (SVM) with Radial Basis Function (rbf) and Bayes classifier. We obtain 96.20% overall accuracy and 93.40% F1-Score for Acmabasi while using Bayes with feature combination as a best result. For Parali region, the highest overall accuracy is obtained with SVM - rbf using feature combination while F1-score is the highest for Bayes classifier with 90.57%.
In-season crop type mapping is essential to agriculture management applications, including yield estimates, crop planting acreage statistics, food market predictions, and land use change analysis that support relevant decision-making, pushing economic development in certain agricultural export nations like Kenya. This study employed a supervised machine learning method to produce three Kenya counties' in-season crop-type maps in September 2023. We used surveyed growing crop ground truth data at the end of August 2023 and European Space Agency (ESA) WorldCover data serving as training labels, including nine crop types (Maize, Coffee, Grassland, Tea, Sugarcane, Exotic tree, Legumes, Vegetable, Native tree). The 15-day composite Sentinel-2 time series data was generated, incorporating training labels to assemble into training samples. They engaged in training a random forest classifier, conducting crop-type classifying in Nandi, Vihiga, and Kisumu Counties of Kenya. Moreover, the majority filter served to refine the classification. The validation results confirmed that grassland, sugarcane, tree, and tea possess high classification accuracy (0.80-0.91), and coffee and maize showcase low accuracy (0.670.73) due to the massive mix pixels. This study attempted to produce in-season crop-type maps in an African nation with fragmented crop fields.
Time-series multispectral remote sensing imagery provides a dynamic representation of crop variations over time, highlighting the disparities in growth conditions among diverse crop types. This method offers a superior capability to differentiate between crop types compared to single temporal phase imagery. However, when applied to practical issues of crop segmentation, challenges persist, including low segmentation accuracy and underutilization of features. To comprehensively address these challenges, we design a new multidimensional multi-attention semantic segmentation network suitable for crop extraction from timeseries multispectral remote sensing images (TSRSnet). Specifically, we propose a multidimensional feature extraction module (MFE) for efficiently mining spatial, temporal and spectral dimensional features in multi-temporal remote sensing images. The module consists of a spatial convolutional layer with temporal modeling capabilities, and a pairwise attention mechanism for joint spatial and channel. Furthermore, we have introduced a difference skip connection module based on a multi-attention mechanism (ADC). This module can accomplish superior performance during the feature fusion phase, contingent on the significance of intra-feature and inter-feature relationships. We experimentally compare the proposed network with a typical semantic segmentation network on the dataset. The results show that the network proposed in this paper has the best segmentation performance and is well suited for the task of crop segmentation in time-series multispectral remote sensing images. The Mean Intersection over Union reached 86.37% and overall accuracy over 93.24%. Through the combination of meticulous feature extraction and multiattention mechanism, our approach improves the segmentation accuracy while better utilizing the multidimensional information of the image, thus realizing the accurate recognition and segmentation of different crops.
Corn (Zea mays) is a significant commodity in Brazil, used for human and animal consumption and biofuel use. This study evaluates the use of PlanetScope Dove and SuperDove images to monitor a central pivot with corn during a growth cycle with surface reflectance and vegetation indices. Its productivity per unit area was also evaluated. We then performed random sampling, extracted surface reflectance spectra, and performed statistical analysis. Results indicated significant surface reflectance variations throughout the crop growth cycle, and the highest accuracy in estimating productivity was in April using gamma distribution and logarithmic function (with an average of 7.88 Mg. ha-1). We argue the PlanetScope Dove and SuperDove images can effectively monitor corn development and estimate its productivity, providing valuable support for agricultural management. In addition, the research demonstrates the potential of machine learning techniques to achieve a relatively accurate estimation of corn productivity at a regional scale.
High-precision estimation of above-ground biomass (AGB) is very crucial for breeding field. Optical variables (e.g. vegetation index (VI)) have widely used in monitoring AGB. In this study, we used a stem-leaf separation strategy to estimate biomass. The combined use of multispectral and deep learning techniques (e.g., convolutional neural network (CNN) and transfer learning (TL)) estimate leaf biomass (LGB). Then, an allometric growth model was used to estimate stem biomass (SGB). We used three-dimensional radiative transfer (3D RTM) - LESS model to simulate a universality and realistic multispectral dataset (n = 44880). We designed a CNN architecture that can extract multi-layer feature of CNNs. This study combined 3D RTM dataset, CNN and TL techniques to estimate maize LGB of multiple growth stage. The results showed our method had the best performance in LGB estimation at multiple growth stage. The result showed that using the allometric growth model to estimate SGB achieved an R-2 of 0.83 and an RMSE of 67.5 g/m(2), improving the prediction accuracy of SGB. This study utilized the advantage of 3D RTM, CNN, TL, and allometric model which can monitor maize AGB more accurately for breeding filed.
In the face of global climate change, agricultural productivity is increasingly under threat, with changes in temperature, precipitation, and drought conditions significantly impacting crop yields and food security. This study presents a comprehensive regional-level analysis, leveraging rich datasets from the Goddard Earth Science Data & Information Center (GES DISC) and the Galaxy Workflow Engine, an open-source science tool enabling Findable, Accessible, Interoperable, and Reusable (FAIR) science. The workflow, executed through Galaxy with high-performance computing resources from the National Science Foundation’s Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support (NSF ACCESS), is applied to selected states in the United States of America and selected countries in Southeast Asia and Africa. The area of interest can be predefined or defined by an arbitrary polygon, enabled by processing capabilities for interoperability on both climate variables and agricultural productivity implemented in the Galaxy toolshed. The Open Geospatial Consortium (OGC) API - Processes service is used for customization services. Advanced analysis techniques, including time series analysis, machine learning, and statistical correlation, are incorporated to assess the impact of climate change on agricultural productivity. By leveraging GES DISC data, Galaxy Climate tools, and NSF ACCESS resources, valuable insights into the impact of climate change on agricultural productivity in various regions are gained. This informs the development of adaptation strategies, improvement of agricultural practices, and ensures long-term food security. The use of Galaxy workflows and GES DISC Giovanni for profiled time series data retrieval contributes to the development of an Open Science workflow, promoting open science principles and enhancing research reproducibility and accessibility. The designed workflow is reusable and can be applied to different regions, enhancing its utility for broader climate change impact assessments.
Improving data interoperability and adherence to standards is critical for Earth Science research and applications. The Earth Science Data Systems (ESDS) Dataset Interoperability Working Group (DIWG) has developed a set of recommendations for data producers to improve data interoperability. A compliance test tool is being developed to compare an Earth Science data file with the DIWG recommendations. This tool focuses on three main areas: checking the names of individual granules, checking metadata compliance (including variable-level metadata, granule-level metadata, and collection-level metadata), and checking data value compliance. The pytest framework, a widely used testing tool in the Python ecosystem, serves as the foundation for this compliance test tool. The compliance test tool is designed to be flexible and adaptable to various environments. It can be run in an isolated virtual environment, a container, or a virtual machine. This flexibility allows for easy integration into different workflows and systems. In addition to the core functionality, the tool also includes Web API services. These services are implemented with a predefined schema, allowing the test to be invoked in a Web environment or in a cloud computing environment. This feature enhances the accessibility and usability of the tool, making it suitable for a wide range of use cases. The tool provides comprehensive compliance reports in multiple formats, including pytest output, JSON, XML, HTML, markdown, or PDF. This feature caters to different use scenarios, making the tool versatile and user-friendly. The effectiveness of the compliance test tool is demonstrated through various case studies. These case studies make use of benchmark datasets from different sources. Some of these sources include samples from HDFGROUP and various Distributed Active Archive Centers (DAACs). A special emphasis is placed on data from the Goddard Earth Sciences Data and Information Services Center (GES DISC). In short, the study presents a comprehensive approach to ensuring data interoperability in Earth science through the implementation of a compliance test tool based on the DIWG recommendations. The tool’s effectiveness is demonstrated through case studies using benchmark datasets, highlighting its potential for widespread use in the field. The tool’s flexibility, adaptability, and comprehensive reporting capabilities make it a valuable resource for data providers aiming to adhere to the DIWG recommendations.
Grazing lands play an important role in providing food for livestock and carbon sequestration. Accurate assessment of grazing land biomass is essential for effective management. However, it is challenging to estimate biomass and other relevant characteristics of grazing lands due to complex environmental factors. This study enhances grazing land analysis for 2021 year in the United States by integrating Earth observation data and machine learning techniques. Unsupervised clustering algorithms were employed based on key environmental factors affecting grazing lands, including precipitation, elevation, land surface temperature, and vegetation cover. Using the Google Earth Engine platform, data from the National Land Cover Database, MODIS, SRTM, and GPM were utilized as inputs for unsupervised clustering. The environmental factors of each cluster were examined for their correlation with reference biomass from the Rangeland Analysis Platform. The results highlight the diversity of environmental conditions within grazing lands and underscore the importance of considering multiple environmental factors for reliable biomass estimation. This research contributes to developing reliable biomass estimation models over a wide range of grazing lands, enhancing the sustainable management of these vital ecosystems.
