Search

Integrating water and nitrogen (N) management is critical to addressing contemporary challenges in agricultural development. This research explored using multispectral sensors mounted on unmanned aerial vehicles (UAVs) to monitor N demand via the normalized difference red-edge (NDRE) vegetation index and consequently schedule fertigation. The experiment included eight treatments with four fertilizer levels under both excessive and full irrigation. The four fertilizer levels comprised: high reference treatment based on commercial lab soil tests, sensor-based treatment triggered by an NDRE saturation threshold of 0.95, deficit treatment with base rate at pre-plant and side-dress, and a control treatment without any N application. The performance of each treatment was evaluated through a comprehensive comparison of yield, water productivity (WP), and nitrogen use efficiency (NUE). The sufficiency index (SI) of sensor-based treatment plots reached a threshold of 0.95, allowing spatially variable adjustment of N application for optimal yield with reduced total N input. Reducing N fertilizer in sensor-based treatments resulted in a substantial reduction of 50 %-60 %, though it led to a yield loss up to 12 %. However, NUE parameters such as partial factor productivity, agronomic efficiency, recovery efficiency, and physiological efficiency improved with sensor-based treatments, alongside reduced N leaching. Combining sensor-based treatment with full irrigation demonstrated the best ecological return, showing relatively lower yield reduction but significant improvements in NUE and WP. Further research into economic returns, saturation threshold algorithms for SI, adaptability to diverse environments, and virtual saturation reference is recommended for the widespread adoption of UAV-based N split management among growers.

Irrigation water management using automated irrigation decision support system (IDSS) as a smart irrigation scheduling tool can improve water use efficiency and crop production, especially under circumstances of limited water supply. The current study evaluated the performance of different artificial intelligence (AI) algorithms and their ensembles in forecasting Crop Evapotranspiration (ETc) and Crop Water Stress Index (CWSI) against calculated single crop coefficient FAO56 ETc and Jackson's theoretical CWSI, respectively. Soil moisture, canopy temperatures (Tc) and Normalized Difference Vegetation Index (NDVI) were all measured from irrigated and non-irrigated maize plots in West Central Nebraska during 2020 and 2021 growing seasons. There were fifteen and twelve input combinations used for ETc and CWSI predictions, respectively, having input variables such as weather and soil moisture as well as ancillary variables, including NDVI, reference evapotranspiration (ETr), and cumulative growing degree days (CGDDs). While evaluating the models, four statistical performance indicators including coefficient of determination (r2), root mean square error (RMSE), mean absoluter error (MAE), and mean absolute percentage error (MAPE) were used. Furthermore, ranking scores were performed on statistical results to find the overall best model across all the input combinations. Based on total ranking scores, CatBoost (RMSE ranging between 0.06 – 0.09 unitless) was the best model in predicting CWSI, while Stacked Regression (RMSE ranging between 0.27 – 0.72 mm d−1) was the best model for ETc estimation. Future research will consider designing and evaluating an IDSS using identified best machine learning models to establish soil water and plant stress feedback for automated irrigation scheduling.