Abstract: Cyberinformatics tools have supported decision makings in agriculture through cutting-edge big data, artificial intelligence/machine learning (AI/ML), and high-performance computing technologies. An open and easy-to-use agricultural cyberinformatics tool based on the findable, accessible, interoperable, reusable (FAIR) data principle is essential for the efficient distribution of crop-specific land cover information. This paper introduces iCrop, a new cyberinformatics tool to enable in-season crop type monitoring for the Conterminous United States (CONUS). As a web-based geographic information system (GIS), iCrop not only delivers three sets of new ML-based field-level crop-specific land cover geospatial data, including pre-season crop cover maps, in-season crop cover maps, and Refined Cropland Data Layer (R-CDL), but also provides a suite of mapping and geoprocessing functionalities through the FAIR geospatial data standards, such as Web Map Service (WMS), Web Coverage Service (WCS), and Web Processing Service (WPS). Meanwhile, we outline several use cases to highlight iCrop’s applications under various agricultural operation scenarios, its functionality for land use change analysis, and its interoperability with generic web-based and desktop GIS software (e.g., GeoPlatform and QGIS). Our experimental results show that the new cyberinformatics tool can provide timely and unique crop-specific land cover information through the geoprocessing functionalities to facilitate U.S. agricultural information management and decision support. Moreover, this paper can be used as a systematic guidance for the design and implementation of the cyberinformatics tool to disseminate agro-geoinformation based on the FAIR data principle.

Full-text access: ScienceDirect

Abstract: Crop-specific land cover mapping is a vital application in agro-geoinformatics with the proliferation of remote sensing data and machine learning techniques. This paper presents a novel approach to enhance the well-known Cropland Data Layer (CDL) product by U.S. Department of Agriculture (USDA) National Agricultural Statistics Service (NASS) using Meta’s Segment Anything Model (SAM). The study leverages SAM’s zero-shot generalization capability to automatically delineate cropland fields from Sentinel-2 images. By voting for the major crop types within each delineated land unit, a substantial number of noisy pixels is CDL can be eliminated, leading to notable improvements in mapping accuracy. Preliminary experimental results across key agricultural regions in the U.S., such as California’s Central Valley and Corn Belt, suggest that SAM can significantly enhance the quality of the original CDL data. This ability to refine crop-specific land cover data, like CDL, demonstrates SAM’s practical applicability within agricultural monitoring systems. Moreover, the result showcases the promising potential of integrating SAM into existing crop type classification workflows to create high-quality early- and in-season crop type maps on a national scale with minimal effort.

Full-text access: ResearchGate, IEEE

Abstract: 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 variety of commonly used VIs, including Normalized Difference Vegetation Index (NDVI), Vegetation Condition Index (VCI), Mean-referenced Vegetation Condition Index (MVCI), Ratio to Median Vegetation Condition Index (RMVCI), and Ratio to previous-year Vegetation Condition Index (RVCI). LANCE enables the NRT monitoring of U.S. cropland vegetation conditions within 24 hours of observation. With more than 20 years of observations, this continuous data set enables geospatial time series analysis and change detection in many research fields such as agricultural monitoring, natural resource conservation, environmental modeling, and Earth system science. The complete set of VI data products described in the paper is openly distributed via Web Map Service (WMS) and Web Coverage Service (WCS) as well as the VegScape web application (https://nassgeodata.gmu.edu/VegScape/).

Full-text access: Nature

Abstract: 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 framework for automatic crop type mapping using spatiotemporal crop information and Sentinel-2 data based on Google Earth Engine (GEE). The main advantage of the framework is using the trusted pixels extracted from the historical Cropland Data Layer (CDL) to replace ground truth and label training samples in satellite images.
OBJECTIVE: This paper will achieve three objectives: (1) assessing spatiotemporal crop information derived from the historical crop cover maps; (2) mapping crop cover, mainly crop fields without regular historical crop rotation patterns, from remote sensing data using supervised learning classification and validating mapping results; and (3) automating in-season crop mapping and exploring the scalability of the framework.
METHODS: The proposed crop mapping workflow consists of four stages. The data preparation stage preprocesses CDL and Sentinel-2 data into the required structure. The spatiotemporal crop information sampling stage extracts trusted pixels from the historical CDL time series and labels Sentinel-2 data. Then a crop type classification model can be trained using the supervised learning classifier in the model training stage. In the mapping/validation stage, an in-season crop cover map over the full Sentinel-2 tile will be produced using the trained model and the classification performance will be validated using CDL or other ground truth data.
RESULTS AND CONCLUSIONS: We systematically perform a group of experiments for in-season mapping of five major crop types (corn, cotton, rice, soybeans, and soybeans-wheat double cropping) over the Mississippi Delta region. The result indicates that the crop cover map of the study area is expected to reach 80%–90% agreement with CDL within the growing season. To further facilitate the use of the framework, we also develop a GEE-enabled online prototype, In-season Crop Mapping Kit, and explore its scalability over agricultural fields in various ecoregions including California, Idaho, Kansas, and Illinois.
SIGNIFICANCE: The mapping-without-ground-truth approach described in this paper can significantly reduce ground truthing process and save substantial resource needs and labor costs, which is applicable to the production of in-season CDL-like data for the entire United States. The findings and outputs will benefit the agriculture community and other agricultural sectors ranging from government, academia, and companies.

Full-text access: ScienceDirect

Abstract: 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 best realized by combining soil moisture estimates with concurrent observations of crop conditions. However, until recently, this capability has not been available to the public. In this paper, we present an interoperable data service application system, the Crop Condition and Soil Moisture Analytics (Crop-CASMA) system, that facilitates the retrieval, analysis, visualization, and sharing of soil moisture data for the CONUS. This system delivers a variety of satellite remote sensing based data products that are derived from Soil Moisture Active Passive (SMAP) Level-4 data and SMAP Thermal Hydraulic disaggregation of Soil Moisture (THySM) data, as well as vegetation index data derived from Moderate Resolution Imaging Spectroradiometer (MODIS) observations. To make services interoperable and reusable, all data products are disseminated via Open Geospatial Consortium (OGC) Web Map Service (WMS) and Web Coverage Service (WCS) interface standards. Additionally, a suite of geoprocessing operations, such as geospatial statistics, time-series profile generation, PDF map production, and image composition, has been implemented in the OGC Web Processing Service (WPS) interface standard. The implementation shows the proposed web service system can significantly simplify the mapping and quantitative analysis of soil moisture and crop condition over U.S. cropland. In addition, it is interoperable with GIS software and has been successfully integrated with web-based applications.

Full-text access: ScienceDirect

Abstract: 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.

Full-text access: ScienceDirect

Abstract: 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.

Full-text access: ResearchGate, IEEE

Abstract: The Cropland Data Layer (CDL) is currently the only subfield level high resolution crop-specific land cover data product over the entire conterminous United States (CONUS). It has been widely used in agricultural industry, business decision support, research, and education worldwide. However, CDL data has its limitations. It is an end-of-season land cover map which is not available within growing season. Moreover, CDLs in early years have many misclassified pixels (rel-atively low accuracy) due to cloud cover and lack of satellite images. This paper will present the studies of using machine learning technique to address these issues in CDL data. Specifically, we will present the design and implementation of a machine learning model for agro-geoinformation discovery from CDL. Several application scenarios of the proposed model, including prediction of crop cover, crop acreage estimation’ in-season crop mapping, and refinement of the early-year CDL data, are demonstrated and discussed.

Full-text access: IEEE

Abstract: Image processing is an essential part of the agricultural observation system. This chapter is the first attempt to provide an overview of the image processing methods, technologies, and tools from the perspective of agro-geoinformatics. First, we introduce the origins, definitions, and basic steps of digital image processing. Along with the traditional image processing hardware and software, the state-of-the-art technologies for agricultural image processing, such as mobile device-based image processing and cloud computing-based image processing, are covered. Image data could be acquired by different sensors in different ways. We discuss three common approaches to collect agricultural image data, in situ, airborne-based, and space-borne-based data collection, as well as the big data challenge in agro-geoinformatics. As the core image processing operation in the agricultural observation system, information extraction aims to understand agro-geoinformation from the raw image data. This chapter also illustrates several image information extraction methods that are widely employed in agro-geoinformatics, such as knowledge-based expert system, machine learning-based decision tree, and artificial neural network. Furthermore, a case study of the production of Cropland Data Layer (CDL) data, a comprehensive, raster-formatted, geo-referenced, annual crop-specific land cover map produced by the U.S. Department of Agriculture (USDA) National Agricultural Statistics Service (NASS), is demonstrated.

Full-text access: Springer

Abstract: Google Earth Engine (GEE) is an ideal platform for large-scale geospatial agricultural and environmental modeling based on its diverse geospatial datasets, easy-to-use application programming interface (API), rich reusable library, and high-performance computational capacity. However, using GEE to prepare geospatial data requires not only the skills of programming languages like JavaScript and Python, but also the knowledge of GEE APIs and data catalog. This paper presents the AgKit4EE toolkit to facilitate the use of the Cropland Data Layer (CDL) product over the GEE platform. This toolkit contains a variety of frequently used functions for use of CDL including crop sequence modeling, crop frequency modeling, confidence layer modeling, and land use change analysis. The experimental results suggest that the proposed software can significantly reduce the workload for modelers who conduct geospatial agricultural and environmental modeling with CDL data as well as developers who build the GEE-enabled geospatial cyberinfrastructure for agricultural land use modeling of the conterminous United States. AgKit4EE is an open source and it is free to use, modify, and distribute. The latest release of AgKit4EE can be imported to any modeling workflow developed using GEE Code Editor (https://code.earthengine.google.com/?accept_repo=users/czhang11/agkit4ee). The source code, examples, documentation, user community, and wiki pages are available on GitHub (https://github.com/czhang11/agkit4ee).

Full-text access: ResearchGate, ScienceDirect

Abstract: As the most widely used crop-specific land use data, the Cropland Data Layer (CDL) product covers the entire Contiguous United States (CONUS) at 30-meter spatial resolution with very high accuracy up to 95% for major crop types (i.e., corn, soybean) in major crop area. However, the quality of early-year CDL products were not as good as the recent ones. There are many erroneous pixels in the early-year CDL product due to the cloud cover of the original Landsat images, which affect many follow-on research and applications. To address this issue, we explore the feasibility of using machine learning technology to refine and correct misclassified pixels in the historical CDLs in this study. An end-to-end deep learning-based framework for restoration of misclassified pixels in CDL image is developed and tested. By feeding the CDL time series into the artificial neural network, a crop sequence model is trained and the misclassified pixels in an original CDL map can be restored. In the experiment with the 2005 CDL data of the State of Illinois, the misclassified pixels over Agricultural Statistics Districts (ASD) #1760 were corrected with a reasonable accuracy (> 85%). The findings suggest that the proposed method provides a low-cost and reliable way to refine the historical CDL data, which can be potentially scaled up to the entire CONUS.

Full-text access: ResearchGate, ISPRS

Abstract: An accurate crop planting map can provide essential information for decision support in agriculture. The method of post-season and in-season crop mapping has been widely studied in the land use and land cover community. However, it remains a challenge to predict the spatial distribution of crop planting before the growing season. This paper is the first attempt to use machine learning approach on the prediction of field-level annual crop planting from historical crop planting maps. We present an end-to-end machine learning framework for crop planting prediction using Cropland Data Layer (CDL) time series as reference data and multi-layer artificial neural network as prediction model. The proposed framework was first tested at Lancaster County of Nebraska State, then scaled up to the U.S. Corn Belt. According to the experiment results from 53 Agricultural Statistics Districts, we found the machine-learned crop planting map was expected to reach 88% agreement with the future CDL. Meanwhile, the crop acreage estimates derived from the machine-learned prediction were highly correlated (R² > 0.9) with the crop acreage estimates of CDL and official statistics by the U.S. Department of Agriculture National Agricultural Statistics Service. This study provides a low-cost and efficient way to predict annual crop planting map, which can be used to support many agricultural applications and decision makings before the beginning of a growing season.

Full-text access: ResearchGate, ScienceDirect

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 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.

Full-text access: ResearchGate, IEEE

Abstract: It is still a challenge to generate the timely crop cover map at large geographic area due to the lack of reliable ground truths at early growing season. This paper introduces an efficient method to extract “trusted pixels” from the historical Cropland Data Layer (CDL) data using crop rotation patterns, which can be used to replace the actual ground truth in the crop mapping and other agricultural applications. A case study in the Nebraska state of USA is demonstrated. The common crop rotation patterns of four major crop types, corn, soybeans, winter wheat, and alfalfa, are compared and analyzed. The experiment results show a considerable number of pixels in CDL following the certain crop sequence during the past decade. Each observed crop type has at least one reliable crop rotation pattern. Based on the reliable crop rotation patterns, a great proportion of pixels can be correctly mapped a year ahead of the release of current-year CDL product. These trusted pixels can be potentially used to label training samples for crop type classification at early growing season.

Full-text access: ResearchGate, IEEE

Abstract: 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.

Full-text access: ResearchGate, ScienceDirect

Abstract: 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 architecture using GeoBrain Cloud, an Apache Cloudstack based private cloud computing platform, and 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 by applying the proposed architecture.

Full-text access: ResearchGate, IEEE

Abstract: GeoPackage, an open format for geospatial information, provides a gateway to bridge agricultural geographic information and mobile devices such as smartphones and tablets. In this paper, we present a Cordova framework based GeoPackage mobile application to support field operations in agriculture. By implementing GeoPackage SDK on mobile application, GeoPackage files can be easily accessed, managed, and visualized in field operation. Based on Cordova framework’s powerful extensibility, the application can be run on multiple mobile platforms such as iOS, Android, and Windows Phone to meet requirement of clients using different types of mobile operating system.

Full-text access: ResearchGate, IEEE

Abstract: Characterized by features of standards-based, platform-independent, portable, self-describing, and compact, GeoPackage, a new open format for geospatial information container, makes it much easier to manipulate geospatial data on mobile devices such as smartphones and tablets. In this paper, we present a GeoPackage based mobile application implementing Common Map API on both Google Maps ^TM and OpenLayers to assist in the manipulation of agricultural data on mobile devices. The app provides geospatial operations to access, manage, analyze, and visualize agricultural data on Google Maps TM and OpenLayers at the same time. Besides, by integrating with Apache Cordova architecture, users are able to run the app on multiple mobile platforms such as iOS and Android with little effort.

Full-text access: ResearchGate, IEEE