Understanding the spatial pattern of soil chemical properties along with the topologic indicators is essential for site-specific agriculture management. A study was conducted on a 50 ha field to investigate the effect of selected topographic indicators, including elevation (DEM), slope (SL), flow accumulation (FA) and Topographic Wetness Index (TWI) on forage crop production. The soil samples and yield data were obtained from the field inventory. Topographical parameters of elevation and slope were estimated with the use of a real-time kinematic global positioning system (RTK-GPS), and then the DEM was generated. The collected soil samples were analyzed for pH, EC, nitrogen and soil organic carbon. Sentinel-2 images were for the creation of yield maps of alfalfa and Rhodes grass. Subsequently, on the basis of DEM, the generated elevation, slope and FA model were then compared with the yield and soil chemical properties. Statistical analysis revealed that the SL, FA and TWI, which are associated with water distribution, were significantly related to crop yields. The FA showed a medium-to-non-significant correlation with the productivity of both alfalfa (R2 = 0.586; p = 0.015) and Rhodes grass (R2 = 0.578; p = 0.01). A significant inverse correlation was recorded between the SL and the yield of both crops (R2 = −0.591 to −0.617; p = 0.01). The yield map revealed that the majority of the area (37.56%) of the experimental field was occupied by the medium-yield class, followed by the high-yield class (33.03%).
Remotely sensed images provide effective sources for monitoring crop growth and the early prediction of crop productivity. To monitor carrot crop growth and yield estimation, three 27 ha center-pivot irrigated fields were studied to develop yield prediction models using crop biophysical parameters and vegetation indices (VIs) extracted from Sentinel-2A (S2) multi-temporal satellite data. A machine learning (ML)-based image classification technique, the random forest (RF) algorithm, was used for carrot crop monitoring and yield analysis. The VIs (NDVI, RDVI, GNDVI, SIPI, and GLI), extracted from S2 satellite data for the crop ages of 30, 45, 60, 75, 90, 105, and 120 days after plantation (DAP), and the chlorophyll content, SPAD (Soil Plant Analysis Development) meter readings, were incorporated as predictors for the RF algorithm. The RMSE of the five RF scenarios studied ranged from 7.8 t ha−1 (R2 ≥ 0.82 with Scenario 5) to 26.2 t ha−1 (R2 ≤ 0.46 with Scenario 1). The optimal window for monitoring the carrot crop for yield prediction with the use of S2 images could be achieved between the 60 DAP and 75 DAP with an RMSE of 8.6 t ha−1 (i.e., 12.4%) and 11.4 t ha−1 (16.2%), respectively. The developed RF algorithm can be utilized in carrot crop yield monitoring and decision-making processes for the self-sustainability of carrot production.
1 January 2018 in International Journal of Agricultural and Biological Engineering