Cotton Yield Estimation From Aerial Imagery Using Machine Learning Approaches

Abstract

Estimation of cotton yield before harvest offers many benefits to breeding programs, researchers and producers. Remote sensing enables efficient and consistent estimation of cotton yields, as opposed to traditional field measurements and surveys. The overall goal of this study was to develop a data processing pipeline to perform fast and accurate pre-harvest yield predictions of cotton breeding fields from aerial imagery using machine learning techniques. By using only a single plot image extracted from an orthomosaic map, a Support Vector Machine (SVM) classifier with four selected features was trained to identify the cotton pixels present in each plot image. The SVM classifier achieved an accuracy of 89%, a precision of 86%, a recall of 75%, and an F1-score of 80% at recognizing cotton pixels. After performing morphological image processing operations and applying a connected components algorithm, the classified cotton pixels were clustered to predict the number of cotton bolls at the plot level. Our model fitted the ground truth counts with an R2 value of 0.93, a normalized root mean squared error of 0.07, and a mean absolute percentage error of 13.7%. This study demonstrates that aerial imagery with machine learning techniques can be a reliable, efficient, and effective tool for pre-harvest cotton yield prediction.

YOLO-C: An Efficient and Robust Detection Algorithm for Mature Long Staple Cotton Targets with High-Resolution RGB Images

“…Most of the existing boll detection methods are based on image segmentation, and the method based on image segmentation to detect and count cotton can be adapted to different scenes and environments by selecting different segmentation algorithms and parameters, which has a certain flexibility and adaptability [5], but its anti-interference ability is poor, which can lead to missed detection or false detection and affect the accuracy and robustness of counting, and the method is sensitive to complex field environments and occlusion. The machine learning-based cotton boll detection method can learn more accurate features and improve the detection ability of the model by manually designing features on the data [9], but there are more influencing factors for cotton boll detection in real environments, and the manual design and selection of features is a huge workload, the correlation between the selected features and the target recognition cannot be guaranteed, and the adaptability and generalization ability of the model is poor. Different data sources also have a great impact on cotton boll detection.…”

“…Li et al used simple linear iterative clustering (SLIC) and density-based Wasserstein distance noise applied spatial clustering (DBSCAN) to generate candidate regions and then fed the histogram-based color and texture features extracted from each candidate region into a random forest for boll marker prediction in field cotton images [8]. Rodriguez-Sanchez et al identified cotton pixels present in remotely sensed images by training a support vector machine (SVM) classifier with four selected features [9]. After performing morphological image processing operations and component concatenation, the classified pixels were clustered to achieve cotton boll number prediction.…”

Unoccupied aerial systems imagery for phenotyping in cotton, maize, soybean, and wheat breeding

“…Use of the ratio of boll pixels over the total image area to predict final yield achieved R 2 values ranging from 0.60 to 0.78 (Maja et al., 2016; Yeom et al., 2018) and up to 0.80 (Yeom et al., 2018). More recently, machine learning (ML) methods have been used to better segment boll pixels from the background and R 2 values of 0.90 were achieved in two independent studies between the image‐predicted and ground‐truth counts (Ashapure et al., 2020; Rodriguez‐Sanchez et al., 2022). It is important to recognize that each study used different genetic resources and environmental variation and thus had different experimental variability.…”

Simulating soil salinity dynamics, cotton yield and evapotranspiration under drip irrigation by ensemble machine learning

“…Cotton (Gossypium barbadense L.) is a crucial economic crop in the world ( Rodriguez-Sanchez et al., 2022 ). It is not only one of the main sources of natural fibers for textiles as well as edible oil ( Ibrahim et al., 2022 ), but also plays an important role in national defense, medicine, the automobile industry, and other fields ( Xu et al., 2021 ).…”

“…Dynamic prediction of soil salinity or EC in drip-irrigated cotton fields based on ML has not been reported. In addition, cotton yield includes not only seed yield, but also lint yield, one of the most important criteria for selecting new lines in breeding ( Rodriguez-Sanchez et al., 2022 ). Hence, we assume that soil salinity, EC, seed yield, lint yield and ET of cotton field under drip irrigation can be predicted by ML and simple input parameters.…”