Title: A New Machine Learning Model to Predict Evapotranspiration: The Dynamic Land Cover Evapotranspiration Model Algorithm (DyLEMa)
Ground-based estimates of evapotranspiration (ET) provide valuable data on local water fluxes but are limited in scale. On the other hand, satellite data offer global ET information but are often incomplete due to clouds or sensor malfunction. To address these limitations, researchers from the University of Illinois have developed a new machine learning model called the Dynamic Land Cover Evapotranspiration Model Algorithm (DyLEMa). This algorithm predicts missing spatial and temporal ET data using trained seasonal machine learning models.
Lead author Jeongho Han, a doctoral student in the Department of Agricultural and Biological Engineering, explained that DyLEMa is a much more detailed and complex model than existing ones. It distinguishes between different land uses, including forest, urban, and agriculture, and different crops, such as corn and soybean. The model includes precipitation, temperature, humidity, solar radiation, vegetation stage, and soil properties, allowing for accurate surface dynamics predictions and ET estimation based on multiple variables.
The researchers evaluated DyLEMa at the scale of Illinois on a daily 30 x 30-meter grid for 20 years using data from NASA, the U.S. Geological Survey, and the National Oceanic and Atmospheric Administration. They tested the model’s accuracy by comparing its results with existing data. For validation over time, they used ground measurements from 2009 to 2016 at four sites in Illinois. Also, to test spatial accuracy, they created artificial scenarios where they inserted a synthetic cloud in a cloud-free image, then applied their algorithm and compared the results with the original data.
DyLEMa reduced ET prediction uncertainty in cumulated ET estimates from an average of +30% (overpredicted) to around -7% (underpredicted) compared to existing measurements, indicating much greater accuracy. The study is part of a larger project on soil erosion funded by the USDA National Institute of Food and Agriculture.
The researchers plan to integrate their data in a distributed hydrological model for better estimation of soil erosion. They believe that the new model can help engage communities and inform policy measures. According to Maria Chu, an associate professor in ABE and the principal investigator on the larger project, “One of the challenges with land management practices is that people may not see the benefit of implementing changes right away. But with this model, we can show that what you are doing now will have a long-term impact, for instance, 10 or 20 years from now and at locations far from your farm. This is the power of using data and computing capacity for informing policy measures.”
The researchers worked with the National Center for Supercomputing Applications (NCSA) and the Illinois Campus Cluster Program (ICCP) to process data and train models. They plan to make their data, including output for 20 years in Illinois, available for other researchers. The new article follows all SEO standards, including keyword optimization, meta descriptions, and appropriate headings.