Agricultural administrative data, which include information collected primarily for administrative purposes by governments and other organizations, are commonly used to improve agricultural statistics. However, one limitation of administrative data is the issue of undercoverage, or the proportion of the target population data that is not represented. If the extent and type of the undercoverage is well understood, adjustments can be made to account for it in the estimation process. The objective of this study is to develop a new method utilizing remote sensing and geospatial data to estimate the extent and type of crop specific administrative data undercoverage in two states in the United States. Preliminary results are reasonable and consistent over a five-year period from 2018 – 2022. The proposed method for estimating the extent and type of crop-specific administrative data undercoverage provides a new tool to improve crop acreage estimation in the U.S.

Crop rotation refers to planting different crops at different times in the same field. Farmers rotate crops to enhance soil fertility, structure, and biodiversity. Scientists and policy makers track crop rotations for environmental assessment, acreage, yield forecasting, and many other applications. Crop prediction, which refers to forecasting the next crop to be planted, is important for statistical applications, agri-business, and climate modeling. Crop prediction is commonly conducted using transition probability models. However, the study of the uncertainty associated with the categorical choice of crops is often neglected. This paper presents two measures of uncertainty for a comprehensive assessment of crop prediction quality. The main objective is to attribute the uncertainty of the prediction errors to specific aleatoric, epistemic, or mechanistic factors. Preliminary results show that these uncertainties are higher for fields with irregular crop rotations.

Early season crop acreage estimation is commonly conducted using crop information collected through large scale agricultural surveys to identify farmers’ planting intentions and decisions. Due to the increased frequency and impact of extreme weather events on agriculture, there is significant interest in developing remote sensing techniques for crop acreage estimation early in the growing season. This paper proposes a new method to produce early season crop acreage estimates for the State of Illinois, United States (U.S), from 2016 to 2019. A geospatial layer of early season crop classifications, known as an Early Season Cropland Data Layer (ESCDL), is created using crop rotation patterns derived from historic USDA National Agricultural Statistics Service (NASS) Cropland Data Layers and current year (March 6 – June 10) satellite imagery. The ESCDL crop specific acreage, derived through pixel counts, are combined with NASS June Area Survey data to obtain unbiased corn and soybean estimates in early June. The ESCDLs are validated using end-of-season Farm Service Agency Common Land Unit and 578 administrative data and have producer and user accuracies from 79.48% to 86.31% for corn, 74.61% to 86.21% for soybeans, and - 4 % to 6 % relative errors when compared to final NASS official estimates.

A novel approach for crop-specific prediction of future crop planting and the development of corresponding uncertainty measures for all predictions is proposed. Using transition probabilities, predictive crop categories are first developed to predict crop-specific planting in the pilot study state of Illinois. Corresponding entropy layers are developed concurrently and can be used to flag survey sample units based on the level of uncertainty associated with the crop predictions. This allows survey units to be prioritized for imputation or for data collection based on whether the predicted value is sufficiently reliable. Further, the predicted acreage is assigned only to those survey units for which the prediction has the potential to be the sufficiently accurate. This approach can provide a solid methodology for reducing survey costs and farmer response burdens without introducing estimation bias or incurring severe losses of statistical efficiency. This has far-reaching implications for the sample design, quality, and timeliness of results for future surveys.

Early season crop identification is important for food security and economic stability. The USDA NASS uses optical data to provide acreage estimates, each June, to the NASS Agricultural Statistics Board. However, early season crop identification is difficult using optical data alone, because imagery is frequently cloudy during the spring. The purpose of this study is to determine whether using SAR and SAR texture can improve early season winter wheat identification compared to optical data alone. Study areas in the Missouri "Bootheel" (2017 growing season) and Northwest Texas (2018 growing season), United States (U.S.) are selected. The SAR data used in this study are Sentinel-1. Optical data include: Landsat 8, Disaster Monitoring Constellation, and Sentinel-2. Study results show that optical data with SAR achieved the highest winter wheat accuracies, 7.7% higher than optical data alone, in Missouri. Optical with SAR and SAR texture resulted in improved accuracies over optical alone, but only marginally, in Texas. These results indicate that optical and SAR, used together, can potentially improve early season crop identification.

The accuracy of a supervised classification is highly dependent upon the training samples. This paper is concerned with the impact of non-proportional training data sampling of imbalanced classes on the land cover classification accuracy, using the See5 decision tree classifier. The purpose of this paper is 1) to examine experimentally how the training sampling ratio affects classification accuracy in the imbalanced class scenario; and 2) to determine the best training data sampling ratio for optimal classification performance using a See5 decision tree classifier. To better measure classification accuracy, we propose a balanced accuracy measure of a targeted class, which incorporates both False Positive and False Negative errors to truthfully reflect the accuracy of a targeted class. The study result indicates that balancing the training sample between classes does not necessarily improve the classification accuracy. Instead, selecting a training sample ratio which equals the actual ratio of the coverages of the imbalanced classes will yield the best classification performance.

Optical based remote sensing plays an important role in citrus crop change monitoring in Florida, United States (U.S). However, persistent cloud cover during the summer growing season in Florida often limits the application of optical sensors. Synthetic Aperture Radar (SAR) has the advantage over optical data by operating at wavelengths not impeded by cloud cover, rain or a lack of illumination. The objective of this study is to assess the effectiveness of using Sentinel-1A C-band SAR data for classifying citrus in Florida. Twelve individual citrus classifications produced using single date optical or SAR data, as well as multi-date optical and SAR data fusion, are designed and tested. It is found that the classification accuracies of Sentinel-l C-band SAR data are slightly lower than those of multi-temporal cloud free optical data (approximately 2.5% difference). However, the relatively comparable classification accuracy results indicate that the Sentinel-1 SAR is a useful alternative imagery source particularly in regions with persistent cloud cover.

Agricultural flood monitoring is important for food security and economic stability. Synthetic Aperture Radar (SAR) has the advantage over optical data by operating at wavelengths not impeded by cloud cover or a lack of illumination. This characteristic makes SAR a potential alternative to optical sensors for agricultural flood monitoring during disasters. The purpose of this study is to assess the effectiveness of using freely available Copernicus Sentinel-1 SAR data for operational agricultural flood monitoring in the United States (U.S.). The operational detection of flood inundation was tested during Hurricane Harvey in 2017, which resulted in significant flooding over Texas and Louisiana, U.S. This paper presents 1) the agricultural flood monitoring method that utilizes Sentinel-1 SAR, the NASS 2016 Cultivated Layer, and the NASS 2016 and 2017 Cropland Data Layers; 2) flood detection validation results and 3) inundated cropland and pasture acreage estimates. The study shows that Sentinel-1 SAR is an effective and valuable data source for operational disaster assessment of agriculture.

Area Sampling Frames are used for surveys including crop acreage and yield, forests, and natural resource inventories and are the foundation of the statistical program of the USDA National Agricultural Statistics Service (NASS) and many statistical survey programs around the world. An automated area frame stratification method was recently implemented into NASS operations, which is based on the objective calculation of percent cultivation derived from the NASS geospatial Cropland Data Layers (CDLs). While autostratification consistently outperforms manual stratification in cultivated areas, we found that CDL-based pixel counting estimation consistently underestimated crop acreage. Previous research indicates that CDL classification accuracy is affected by training data pixel level buffering. We hypothesize that training data pixel level buffering will also affect the CDL based auto-stratification results and crop acreage estimation. This paper evaluates the impact of training data buffering on area frame stratification results and crop estimates. Preliminary results indicate that the crop acreage underestimation can be directly attributed to the training data pixel level buffering procedure.

Area Sampling Frames (ASFs) are the foundation of the agricultural statistics program of USDA National Agricultural Statistics Service (NASS). A geospatial Cropland Data Layer (CDL) based automated stratification (AS) method was recently implemented to achieve higher accuracies than traditional stratification (TS), based on visual interpretation, in cultivated areas. This paper extends the AS assessment to the post stratification estimates. South Dakota (SD) US 2013 post stratification estimates, based on AS, are compared with the SD 2013 June Agricultural Survey estimates based on TS. Post stratification estimates obtained using AS are comparable, to the TS estimates, based on estimate percent differences. Considering the significant improvement in accuracy using AS in cultivated strata in five test states, improved accuracy in the highly cultivated stratum and improved stratum homogeneity in this study, it is concluded that the CDL based AS method generates ASFs that are more objective, efficient, accurate, and homogeneous and reduces labor costs.

Timely, frequent, crop vegetation condition information, with complete geospatial coverage acquired throughout the growing season is critical for public and private sector decision making that concerns agricultural policy, production, food security, and food prices. The NASA Soil Moisture Active and Passive (SMAP) mission provides such a reliable data source for cropland soil moisture assessment. This paper presents a prototype of an interactive Web service based SMAP soil moisture visualization, dissemination and analytics system for US soil moisture monitoring based on the VegScape framework. This system automatically retrieves and preprocesses SMAP soil moisture data for US cropland soil moisture condition monitoring and assessment. The prototype takes advantage of the VegScape's service oriented architecture and adds a new component for SMAP soil moisture. It reuses existing VegScape visualization, dissemination and analytical functionalities and tools. The prototype inherits the capabilities of interactive map operations, data dissemination, statistical tabulating and charting, comparison analysis, and various Web services.

This paper proposes a novel method for land cover area frame stratification based on corn planting frequency and percent cultivation. South Dakota U.S. geospatial crop frequency (2008-2013) and cultivation (2013) data layers created from NASS Cropland Data Layers are utilized to develop a novel area sampling frame (ASF) stratification design. Eight corn planting frequency strata are derived using a k-means clustering method based on mean corn planting frequency calculated at the NASS ASF primary sampling unit level. The corn planting frequency strata are then sub stratified based on percent cultivation, which, together, provide more crop specific information than the current NASS ASF based on percent cultivation alone. Using 2014 Farm Service Agency Common Land Unit Data as in situ validation, it is found that this novel ASF design predicts crop specific planting patterns well. These results indicate that the new stratification method has potential to improve ASF accuracy, efficiency and crop estimates.

A new automatic stratification method utilizing USDA National Agricultural Statistics Service (NASS) geospatial Cropland Data Layers (CDLs) was recently implemented in NASS operations. Recent research findings indicated that using the CDL stratification method rather than visual interpretation of satellite imagery and aerial photography (traditional method) to define percent cultivation of land areas resulted in Area Sampling Frames (ASF) constructed with improved accuracy, objectivity and efficiency at reduced cost [3]. This paper describes an operational ASF construction process that integrates the automated CDL stratification results with traditional editing/review procedures, a hybrid approach. New 2013/2014 ASFs for South Dakota and Oklahoma were successfully built using the new operational process and illustrated significant improvements in frame accuracy, operational efficiency, and cost.

The National Agricultural Statistics Service (NASS) Area Sampling Frames (ASFs) are based on the stratification of US land cover by percent cultivation. Recently, an automated stratification method based on the NASS Cropland Data Layer (CDL) was developed to efficiently and objectively stratify US land cover. This method achieved higher accuracies in all cultivated strata with statistical significance at a 95% confidence level. This paper proposed to develop crop specific covariate data based on 2007 - 2010 CDLs. Crop (corn, soybeans, wheat and cotton) and non crop (forest, urban and water) covariate data were derived and validated for six states. Producer and user accuracies for the covariate data sets were based on independent 2011 Farm Service Agency Common Land Unit data and 2011 CDLs. Non crop covariate data were validated using the National Land Cover Data 2006. Covariate data were used within NASS to conduct substratification of the 2013 Oklahoma ASF.

This paper describes the method used to derive 30 meter resolution 2011 US cultivated data sets based on multi-year National Agricultural Statistics Service (NASS) Cropland Data Layer (CDL) data. This paper presents different sets of rules (models) to build the cultivated data sets, and a comparison of the resulting cultivated data set accuracies to the accuracies of the original CDL input data. Nine models to create 2011 cultivated data sets for nine US states are tested. Each model provides a set of rules for merging pixels of multi-year (2007-2011) CDL data. The cultivated data accuracy was assessed against in situ 2011 Farm Service Agency (FSA) Common Land Unit (CLU) data. It was found that accuracies were close among the cultivated data generated using the different models. The strongest models for all states achieved overall (producer and user) accuracies greater than 94% for cultivated and non cultivated categories.