Cover Crop Biomass Predictions with Unmanned Aerial Vehicle Remote Sensing and TensorFlow Machine Learning

The continuous assessment of cover crop growth throughout the season is a crucial baseline observation for making informed crop management decisions and sustainable farming operation. Precision agriculture techniques involving applications of sensors and unmanned aerial vehicles provide precise and prompt spectral and structural data, which allows for effective evaluation of cover crop biomass. Vegetation indices are widely used to quantify crop growth and biomass metrics. The objective of this study was to evaluate the accuracy of biomass estimation using a machine learning approach leveraging spectral and canopy height data acquired from unmanned aerial vehicles (UAVs), comparing different neural network architectures, optimizers, and activation functions. Field trials were carried out at two sites in Louisiana involving winter cover crops. The canopy height was estimated by subtracting the digital surface model taken at the time of peak growth of the cover crop from the data captured during a bare ground condition. When evaluated against the validation dataset, the neural network model facilitated with a Keras TensorFlow library with Adam optimizers and a sigmoid activation function performed the best, predicting cover crop biomass with an average of 96 g m−2 root mean squared error (RMSE). Other statistical metrics including the Pearson correlation and R2 also showed satisfactory conditions with this combination of hyperparameters. The observed cover crop biomass ranged from 290 to 1217 g m−2. The present study findings highlight the merit of comprehensive analysis of cover crop traits using UAV remote sensing and machine learning involving realistic underpinning biophysical mechanisms, as our approach captured both horizontal (vegetation indices) and vertical (canopy height) aspects of plant growth.