Utilizing Machine Learning and Hyperspectral Data to Decode Growth Patterns, Cultivar Identification, and Yield Dynamics in Potato Cultivation

Abstract

Abstract Understanding growth patterns, cultivar identification, and yield dynamics in potato cultivation is essential for optimizing agricultural practices and improving productivity. This study leverages machine-learning techniques to analyze and predict potato growth stages, identify cultivars, and forecast yield outcomes based on hyperspectral data, environmental factors, and physiological traits. Various machine-learning models were developed using multispectral imaging, soil parameters, and climatic factors collected across diverse cultivation environments. The models were evaluated for their accuracy in classifying potato cultivars, identifying growth stages, and predicting yield performance. Key physiological trends were identified during the tuber initiation, bulking, and maturation phases, correlating with specific environmental conditions. Predictions for tuber yield showed high accuracy, with models achieving R² values above 0.90 across validation datasets. Additionally, this study highlights the importance of integrating machine learning with precision agriculture systems to enhance decision-making and resource management. The proposed methodology demonstrates significant potential for advancing potato-farming practices by providing actionable insights into growth monitoring, cultivar differentiation, and yield optimization.

Plant phenotyping relevance

機械学習とハイパースペクトル／マルチスペクトルデータを用いて、ジャガイモの生育段階・品種・収量を推定する手法を開発・評価しており、植物形質の取得・推定が中心である。

Code and data availability

The paper's hyperspectral, growth, and yield measurements are paper-specific, but the Data Availability Statement says they are available only on request from the corresponding author. Mentions of ICAR-CRIDA, USGS, NOAA, ECMWF, and CIP are generic external repositories without a paper-specific deposit identifier or URL

No evidence-backed public reproduction asset is currently recorded.