Embedded Files
GeoAI for Land-Water-Food Solutions
GeoAI for Land-Water-Food Solutions
Agricultural Irrigation
Irrigation frequency (number of years irrigated between 1997-2017) across the US
U.S. Irrigation
Supported by USGS, NASA, TWDB, DRI
Irrigation plays a critical role in US food security and agricultural economy. Despite its importance, substantial uncertainties remain regarding how irrigation affects water use and environmental sustainability. In this research focus, we integrate multi-source geospatial data, AI/ML techniques, and physics-based models to develop user-centered tools that provide fundamental, field-scale information to support improved water management. Specifically, our work aims to quantify:
(1) where irrigated croplands are and how they change over time
(2) what are the techniques used for irrigation and their efficiencies
(3) how much water is extracted and where the water is from
Related publications:
Martin et al., 2025. Estimating irrigation consumptive use for the conterminous United States: coupling satellite-sourced estimates of actual evapotranspiration with a national hydrologic model. Journal of Hydrology, 133909.
Xie Y., Gibbs H., and Lark T.J., 2021. "LANID-US: annual 30-m resolution irrigation maps for the conterminous United States, 1997-2017." Earth System Science Data, 13(12), 5689-5710. https://doi.org/10.5194/essd-13-5689-2021.
Xie Y. and Lark T.J., 2021. " Mapping annual irrigation from Landsat imagery and environmental variables across the conterminous United States." Remote Sensing of Environment, 260, 1-17. https://doi.org/10.1016/j.rse.2021.112445.
Ren J., Shao Y., Wan H., and Xie Y., 2021. "A two-step mapping of irrigated corn with multi-temporal MODIS and Landsat Analysis Ready Data." ISPRS Journal of Photogrammetry and Remote Sensing, 176, 69-82. https://doi.org/10.1016/j.isprsjprs.2021.04.007.
Xie Y., Lark T. J., Brown J. F., & Gibbs H. K., 2019. "Mapping irrigated cropland extent across the conterminous United States at 30 m resolution using a semi-automatic training approach on Google Earth Engine." ISPRS Journal of Photogrammetry and Remote Sensing, 155, 136-149. https://doi.org/10.1016/j.isprsjprs.2019.07.005.
Global Irrigation
Supported by foundation
Globally, irrigated croplands account for approximately 20% of total agricultural land yet consume nearly 70% of worldwide freshwater withdrawals. Compared to the United States, reliable irrigation data are even more limited at the global scale. In this research focus, we extend our U.S.-based work globally by developing scalable ML methods to produce high-resolution irrigation infrastructure maps with update frequencies of one to five years to support more robust global water resource/use assessments.
Related publications:
Zhang, L., Xie, Y., Zhu, X., Ma, Q., & Brocca, L., 2024. CIrrMap250: Annual maps of China’s irrigated cropland from 2000 to 2020 developed through multisource data integration. Earth System Science Data Discussions, 2024, 1-31. https://doi.org/10.5194/essd-16-5207-2024.
Zhang, C., Dong, J., Xie, Y., Zhang, X., & Ge, Q., 2022. Mapping irrigated croplands in China using a synergetic training sample generating method, machine learning classifier, and Google Earth Engine. International Journal of Applied Earth Observation and Geoinformation, 112, 102888.
Agricultural Land Use
Supported by DOE, Rainforest Alliance
Agricultural land use is very dynamic, ranging from crop type changes to fallow, abandonment/retirement, and conversion. Our research focus on agricultural land use aims to understand the spatial and temporal dynamics of croplands and management practices under increasing climate, water, and food system pressures. We integrate multi-source satellite observations, geospatial analytics, and ML methods to map agricultural land use and management practices at field to national scales. This work emphasizes consistency, scalability, and update frequency, enabling the detection of land-use change, cropping system transitions, and responses to climate variability and policy drivers.
Related publications:
Xie, Y., Spawn-Lee, S. A., Radeloff, V. C., Yin, H., Robertson, G. P., & Lark, T. J., 2024. Cropland abandonment between 1986 and 2018 across the United States: spatiotemporal patterns and current land uses. Environmental Research Letters, 19(4), 044009. https://doi.org/10.1088/1748-9326/ad2d12.
Yin et al., 2020. Monitoring cropland abandonment with Landsat time series. Remote Sensing of Environment, 246, 111873.
Uludere Aragon, N., Xie, Y., Bigelow, D., Lark, T. J., & Eagle, A. J., 2024. The realistic potential of soil carbon sequestration in US croplands for climate mitigation. Earth's Future, 12(6), e2023EF003866.
US cropland abandonment/retirement, 1986-2018
Ag-urban Interactions
Land use competition
Supported by AFT
The earth has undergone unprecedented urbanization in recent decades and the global development of land consumes some of our planet’s most productive agricultural lands. This conversion is usually irreversible—once urbanized, agricultural lands are very unlikely to be recultivated. Such losses of agricultural lands already pose a substantial threat to local and regional food security. It is projected that the trends of urbanization-induced cropland loss will continue if no actions are taken. Given an increasing population and its attendant growing need for food and fuel, protecting existing agricultural lands is critical, especially under the compounding stresses of climate change, extreme weather, armed conflicts, and public health crises such as the COVID-19 pandemic.
In this research focus, we are integrating multi-source geospatial data, land use science, and machine learning to understand complex agri-urban land use competitions with the aim of saving limited lands for both food security and sustainable urban development. More specifically, our research covers:
(1) map, monitor, and project urbanization and cropland dynamics
(2) understand the urbanization process of agriculture lands
(3) predict and protect croplands under threat of urbanization
(4) translate our scientific findings into actionable changes
Related publications:
Xie, Y., Hunter, M., Sorensen, A., Nogeire-McRae, T., Murphy, R., Suraci, J.P., Lischka, S., Lark, T.J., 2023. U.S. Farmland under Threat of Urbanization: Future Development Scenarios to 2040. Land, 12, 574. https://doi.org/10.3390/land12030574.
Xie Y., Weng Q., and Fu P., 2019. "Temporal variations of artificial nighttime lights and their implications for urbanization in the conterminous United States, 2013–2017." Remote Sensing of Environment, 225: 160-174. https://doi.org/10.1016/j.rse.2019.03.008.
Xie Y. and Weng Q., 2017. "Spatiotemporally enhancing time-series DMSP/OLS nighttime lights for mapping large-scale urban dynamics." ISPRS Journal of Photogrammetry and Remote Sensing 128: 1-15. https://doi.org/10.1016/j.isprsjprs.2017.03.003.
Xie Y. and Weng Q., 2016. "Updating urban extents with nighttime light imagery by using an object-based thresholding method." Remote Sensing of Environment 187: 1-13. https://doi.org/10.1016/j.rse.2016.10.002.
US cropland under threat of urbanization by 2040
Water use conflicts
Supported by foundation & industry
Water use competition between urban and agricultural sectors is a complex and pressing issue, particularly in regions where water resources are limited. Residential demands for water, driven by population growth and urbanization, often clash with the needs of agriculture, which relies heavily on irrigation to sustain crop production. This competition intensifies during periods of drought or water scarcity, which are further exacerbated by the unpredictability of climate change.
To better understand ag-urban water competition and ensure more sustainable use of this vital resource, we are developing geospatial, data-driven, and machine learning models to:
(1) estimate residential and agricultural irrigation water use
(2) identify areas where agricultural and residential water use conflict
(3) enhance water resource management at agriculture-urban interfaces
Global water stress level (Sources: World Resources Institute; United Nations)
Page updated
Google Sites
Report abuse