An accurate stand count is a prerequisite to determining the emergence rate, assessing seedling vigor, and facilitating site-specific management for optimal crop production. Traditional manual counting methods in stand assessment are labor intensive and time consuming for large-scale breeding programs or production field operations. This study aimed to apply two deep learning models, the MobileNet and CenterNet, to detect and count cotton plants at the seedling stage with unmanned aerial system (UAS) images. These models were trained with two datasets containing 400 and 900 images with variations in plant size and soil background brightness. The performance of these models was assessed with two testing datasets of different dimensions, testing dataset 1 with 300 by 400 pixels and testing dataset 2 with 250 by 1200 pixels. The model validation results showed that the mean average precision (mAP) and average recall (AR) were 79% and 73% for the CenterNet model, and 86% and 72% for the MobileNet model with 900 training images. The accuracy of cotton plant detection and counting was higher with testing dataset 1 for both CenterNet and MobileNet models. The results showed that the CenterNet model had a better overall performance for cotton plant detection and counting with 900 training images. The results also indicated that more training images are required when applying object detection models on images with different dimensions from training datasets. The mean absolute percentage error (MAPE), coefficient of determination (R²), and the root mean squared error (RMSE) values of the cotton plant counting were 0.07%, 0.98 and 0.37, respectively, with testing dataset 1 for the CenterNet model with 900 training images. Both MobileNet and CenterNet models have the potential to accurately and timely detect and count cotton plants based on high-resolution UAS images at the seedling stage. This study provides valuable information for selecting the right deep learning tools and the appropriate number of training images for object detection projects in agricultural applications.

Surface soil water content (SWC) is a major determinant of crop production, and accurately retrieving SWC plays a crucial role in effective water management. Unmanned aerial systems (UAS) can acquire images with high temporal and spatial resolutions for SWC monitoring at the field scale. The objective of this study was to develop an algorithm to retrieve SWC by integrating soil texture into a vegetation index derived from UAS multispectral and thermal images. The normalized difference vegetation index (NDVI) and surface temperature (T_s) derived from the UAS multispectral and thermal images were employed to construct the temperature vegetation dryness index (TVDI) using the trapezoid model. Soil texture was incorporated into the trapezoid model based on the relationship between soil texture and the lower and upper limits of SWC to form the texture temperature vegetation dryness index (TTVDI). For validation, 128 surface soil samples, 84 in 2019 and 44 in 2020, were collected to determine soil texture and gravimetric SWC. Based on the linear regression models, the TTVDI had better performance in estimating SWC compared to the TVDI, with an increase in R² (coefficient of determination) by 14.5% and 14.9%, and a decrease in RMSE (root mean square error) by 46.1% and 10.8%, for the 2019 and 2020 samples, respectively. The application of the TTVDI model based on high-resolution multispectral and thermal UAS images has the potential to accurately and timely retrieve SWC at the field scale.

Understanding and accurately predicting within-field spatial variability of crop yield play a key role in site-specific management of crop inputs such as irrigation water and fertilizer for optimized crop production. However, such a task is challenged by the complex interaction between crop growth and environmental and managerial factors, such as climate, soil conditions, tillage, and irrigation. In this paper, we present a novel Spatial-temporal Multi-Task Learning algorithms for within-field crop yield prediction in west Texas from 2001 to 2003. This algorithm integrates multiple heterogeneous data sources to learn different features simultaneously, and to aggregate spatial-temporal features by introducing a weighted regularizer to the loss functions. Our comprehensive experimental results consistently outperform the results of other conventional methods, and suggest a promising approach, which improves the landscape of crop prediction research fields.