Plant-level prediction of potato yield using machine learning and unmanned aerial vehicle (UAV) multispectral imagery

• Published in: Discover applied sciences Vol. 6; no. 12; pp. 649 - 11
• Main Authors: Tatsumi, Kenichi, Usami, Tamano
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 29.11.2024; Springer Nature B.V; Springer
• Subjects: Accuracy; Agricultural production; Algorithms; Applied and Technical Physics; Biomass; Calibration; Chemistry/Food Science; Crop yield; Data collection; Earth Sciences; Engineering; Environment; Feature selection; Growing season; Harvest; High resolution; Image enhancement; Image resolution; Learning algorithms; Machine learning; Materials Science; Optimization; Parameter identification; Plant-level yield; Plants; Plants (botany); Potassium; Potato yield; Potatoes; Precision agriculture; Predictions; Random variables; Regression analysis; Remote sensing; Sensors; Statistical analysis; Statistical models; Support vector machines; Unmanned aerial vehicle; Unmanned aerial vehicles; Variables; Vegetables; Vegetation; Vegetation index; United States > US; China; Feature selection; Plant-level yield; Unmanned aerial vehicle; Optimization; Potato yield; Machine learning
• ISSN: 3004-9261; 2523-3963; 3004-9261; 2523-3971
• DOI: 10.1007/s42452-024-06362-7

This study presents a new method for predicting the underground yield of potato at the plant level, using two key approaches: (1) identifying the critical variables for yield prediction based on plant height and vegetation index (VI) maps derived from unmanned aerial vehicle (UAV) imagery; (2) evaluating the accuracy of predictions for fresh tuber weight (FTW), number of tubers (NMT), and fresh weight per tuber (FWT), using various machine learning (ML) algorithms. During the growing season of 2022, high-resolution red, green, and blue light and multispectral images were collected weekly using a UAV. In total, 648 variables, including first- and second-order statistical parameters, were extracted from the images. Five feature-selection algorithms were used to identify the key variables influencing the predictions of FTW, NMT, and FWT. Furthermore, ML models, including random forest (RF), ridge regression, and support vector machines, were employed to refine the variable sets for ensuring stable yield component predictions. The results highlighted the importance of considering first- and second-order statistical parameters derived from plant height and VI. Second-order statistics were crucial for predicting the FTW and FWT. The RF model demonstrated high prediction accuracy, with R 2 values of 0.57, 0.45, and 0.49 for FTW, NMT, and FWT, respectively, using the best feature selection method. Thus, leveraging RGB and multispectral imagery data recorded that 1.5–2 months before harvest can significantly enhance yield predictions conducted using ML models. The proposed methodology can help farmers growing potatoes or other crops optimize cultivation and predict the yield. Article highlights High-resolution UAV imagery was used to effectively predict potato yield from plant height and vegetation indices. Feature selection algorithms identified key variables that significantly enhanced the application of machine learning models. Machine learning, especially the random forest model, accurately predicted yield components, showcasing potential applications in precision agriculture.