The tillage suitability product is a per-crop, per-pixel (30 square-meters) model representation of the predicted probability (0.00-1.00) that an area can support commodity crop development for a suite of crop types commonly grown in the LCD landscape. The values for each grid cell are interpreted as a probability, with any value greater-than 0.50 suggesting an area should be suitable for crop development based on observations of 2.5 million farmed areas around the LCD geography. To demonstrate composite suitability (“tillage”) for all crops, we added the individual probabilities for our modeled from cover classes (cereals, corn, cotton, and beans), which represents the overall proportion of votes for “crop” vs. “not-crop/other” for trees in our full Random Forest model. To predict commodity crop development suitability in 2050, we used the commodity crop suitability model (described above), fit to current soil, climate, aquifer groundwater, and topographic conditions for 2016, and replaced the model input data with a raster of projected aquifer saturated thickness for 2050 and re-ran our model prediction (described above). Note that we held climate variables constant for this analysis (under 2016 conditions), in order to demonstrate how groundwater availability, which our model suggested was the predominant driver of crop suitability for the LCD region, may influence suitability.
