Precision Agriculture Using Soil Sensor Driven Machine Learning for Smart Strawberry Production.

Abstract

Ubiquitous sensor networks collecting real-time data have been adopted in many industrial settings. This paper describes the second stage of an end-to-end system integrating modern hardware and software tools for precise monitoring and control of soil conditions. In the proposed framework, the data are collected by the sensor network distributed in the soil of a commercial strawberry farm to infer the ultimate physicochemical characteristics of the fruit at the point of harvest around the sensor locations. Empirical and statistical models are jointly investigated in the form of neural networks and Gaussian process regression models to predict the most significant physicochemical qualities of strawberry. Color, for instance, either by itself or when combined with the soluble solids content (sweetness), can be predicted within as little as 9% and 14% of their expected range of values, respectively. This level of accuracy will ultimately enable the implementation of the next phase in controlling the soil conditions where data-driven quality and resource-use trade-offs can be realized for sustainable and high-quality strawberry production.

Plant phenotyping relevance

土壌センサーデータと機械学習を用いて収穫時のイチゴ果実形質（色、可溶性固形分など）を推定し、予測精度も評価しているため、果実形質推定手法が中心である。

Code and data availability

The paper's soil-sensor/quality dataset and analysis code are stated to be openly available in a Mendeley repository (doi 10.17632/87stbx334b.1), which is a paper-specific public asset. However, no Mendeley URL appears in the allowed_urls list, so no actionable asset with a permitted URL can be reported. Other allowed-

No evidence-backed public reproduction asset is currently recorded.