JDS Journal of Data Science 1683-86021680-743X1680-743X School of Statistics, Renmin University of China JDS1215 10.6339/25-JDS1215 Computing in Data Science Quantifying the Sensitivity of Land Use Land Cover Metrics Through Simulation Techniques BurgerHaleyA02425259@usu.edu1∗ BeanBrennanbrennan.bean@usu.edu Department of Mathematics and Statistics, Utah State University, United States Corresponding author. Email: A02425259@usu.edu. 20261912026242436454158202519122025 2026 The Author(s). Published by the School of Statistics and the Center for Applied Statistics, Renmin University of China.2026 Open access article under the CC BY license.

Land use land cover (LULC) change in the agriculture, is a critical area of concern as it directly impacts food security, environmental health, and economic stability. One of the leading LULC data products is the U.S. Department of Agriculture’s (USDA) Cropland Data Layer (CDL). Produced annually by the USDA National Agricultural Statistics Service (NASS) using satellite imagery, the CDL provides crop-specific data with an estimated classification accuracy of 85% to 95% for major crop types across the U.S. However, several limitations inherent to the CDL, such as crop underestimation bias, pixel misclassification, and difficulty distinguishing certain vegetation types, have raised questions about the accuracy of LULC change estimates derived from this dataset. In this paper, we introduce the R package cdlsim, designed to quantify the sensitivity of CDL-derived metrics through simulations of CDL data at the patch level using NASS published accuracy statistics. We present a case study utilizing landscape metrics calculated with the popular landscapemetrics R package to demonstrate the utility of cdlsim in quantifying the sensitivity of metrics to random perturbations in the data. The case study examines a mixed agricultural and grassland landscape in South Dakota, illustrating how our package enables researchers to achieve a more nuanced representation of land-use change.

 Cropland Data Layer (CDL) landscape metrics sensitivity analysis simulation References Araújo MB, Guisan A (2006). Five (or so) challenges for species distribution modelling. Journal of Biogeography, 33(10): 1677–1688. https://doi.org/10.1111/j.1365-2699.2006.01584.x Boryan C, Yang Z, Mueller R, Craig M (2011). Monitoring US agriculture: The US Department of Agriculture, National Agricultural Statistics Service, Cropland Data Layer Program. Geocarto International, 26(5): 341–358. https://doi.org/10.1080/10106049.2011.562309 Burger H (2025). cdlsim: Simulation of classification uncertainty in usda cropland data layer (cdl) products. https://github.com/burgerhaley97/cdlsim Chiarucci A, Enright NJ, Perry GLW, Miller BP, Lamont BB (2003). Performance of nonparametric species richness estimators in a high diversity plant community. Diversity and Distributions, 9(4): 283–295. https://doi.org/10.1046/j.1472-4642.2003.00027.x Copenhaver K, Hamada Y, Mueller S, Dunn JB (2021). Examining the characteristics of the Cropland Data Layer in the context of estimating land cover change. ISPRS International Journal of Geo-Information, 10(5): 281. https://doi.org/10.3390/ijgi10050281 Dubos N, Préau C, Lenormand M, Papuga G, Monsarrat S, Denelle P, et al. (2022). Assessing the effect of sample bias correction in species distribution models. Ecological Indicators, 145: 109487. https://doi.org/10.1016/j.ecolind.2022.109487 Hesselbarth MH, Sciaini M, With KA, Wiegand K, Nowosad J (2019). landscapemetrics: An open-source R tool to calculate landscape metrics. R package version 2.2.1. Hijmans RJ (2025). terra: Spatial Data Analysis. R package version 1.8-42. Hunt K, Abernethy J, Beeson P, Bowman M, Wallander S, Williams R (2024). Crop sequence boundaries using usda national agricultural statistics service historic cropland data layers. Statistical Journal of the IAOS, 40: 1–10. https://doi.org/10.3233/SJI-230078 Kline K, Singh N, Dale V (2013). Cultivated hay and fallow/idle cropland confound analysis of grassland conversion in the western Corn Belt. PNAS, 110(31): E2863. Laingen C (2015). Measuring cropland change: A cautionary tale. Papers in Applied Geography, 1(1): 65–72. https://doi.org/10.1080/23754931.2015.1009305 Lark TJ, Mueller RM, Johnson DM, Gibbs HK (2017). Measuring land-use and land-cover change using the U.S. Department of Agriculture’s Cropland Data Layer: Cautions and recommendations. International Journal of Applied Earth Observation and Geoinformation, 62: 224–235. https://doi.org/10.1016/j.jag.2017.06.007 Lark TJ, Schelly I, Gibbs H (2021). Accuracy, bias, and improvements in mapping crops and cropland across the United States using the USDA Cropland Data Layer. Remote Sensing, 13(5): 968. https://doi.org/10.3390/rs13050968 Lin L, Di L, Zhang C (2022). Validation and refinement of Cropland Data Layer using a spatial-temporal decision tree algorithm. Sci Data, 9(63). Lisic J, Chen L, Stachelek J (2024). Tools to download and work with USDA Cropscape Data. R package version 1.13. McGarigal K, Marks BJ (1995). FRAGSTATS: Spatial pattern analysis program for quantifying landscape structure. United States Department of Agriculture Pacific Northwest Research Station. NASS (2023). Frequently anticipated questions. Accessed: 2024-07-01. Pritsolas J, Pearson R (2021). A cautionary tale: A recent paper’s use of research based on the USDA Cropland Data Layer to assess the environmental impacts of claimed cropland expansion. Reitsma KD, Clay DE, Clay SA, Dunn BH, Reese C (2016). Does the U.S. Cropland Data Layer provide an accurate benchmark for land-use change estimates? Agronomy, 108(1): 266–272. https://doi.org/10.2134/agronj2015.0288 Robinson OJ, Ruiz-Gutierrez V, Fink D (2018). Correcting for bias in distribution modelling for rare species using citizen science data. Diversity and Distributions, 24(4): 460–472. https://doi.org/10.1111/ddi.12698 Siqueira T, Pessoa L, Vieira L (2023). Evaluating land use impacts on water quality: Perspectives for watershed management. Sustainable Water Resources Management, 9(192). https://doi.org/10.1007/s40899-023-00968-2 Smith EP, van Belle G (1984). Nonparametric estimation of species richness. Biometrics, 40(1): 119–129. https://doi.org/10.2307/2530750 United States Department of Agriculture, Natural Resources Conservation Service (2025). Geospatial data gateway. Accessed: 2024-05-19. US Environmental Protection Agency (2025). Ecoregions of North America. Accessed: 2025-02-01. USDA (2024). Cropland Data Layer: USDA NASS, Marketing and Information Services Office. Washington, D.C. Wright CK, Wimberly MC (2013a). Recent land use change in the western Corn Belt threatens grasslands and wetlands. PNAS, 110(10): 4134–4139. https://doi.org/10.1073/pnas.1215404110 Wright CK, Wimberly MC (2013b). Reply to Kline et al.: Cropland Data Layer provides a valid assessment of recent grassland conversion in the western Corn Belt. PNAS, 110(31): E2853. Zhang C, Marfatia P, Farhan H, Di L, Lin L, Zhao H, et al. (2023). Enhancing USDA NASS Cropland Data Layer with Segment Anything Model. In: 2023 11th International Conference on Agro-Geoinformatics (Agro-Geoinformatics). (Agro-Geoinformatics 2023 Organizing Committee, eds.), 1–5. Zhang C, Yang Z, Di L, Lin L, Hao P, Guo L (2021). Applying machine learning to Cropland Data Layer for agro-geoinformation discovery. In: IEEE International Geoscience and Remote Sensing Symposium IGARSS. (D Miralles, C Persello, K Beenen, eds.), Brussels, Belgium. 2021, 9554628.