Temporal-Aware Hybrid Machine Learning for Nutrient Prediction in Precision Tomato Cultivation

Precise nutrient management strategies should consider the variability in crop growth and cultivation periods in precision agriculture. This paper proposes a temporal-aware hybrid machine learning approach based on Ridge Regression and Least-Squares Regression (LSR) for predicting soil nitrogen (N), phosphorus (P), and potassium (K) in precision tomato cultivation. The dataset comprises 180 observations collected over three cultivation periods, including soil, climate, and plant attributes. The proposed approach was evaluated using a standard random 80:20 train–test split and an unseen-period validation strategy to assess temporal generalization. The hybrid model produced an average R2 of 0.94 and 0.90 in the conventional and unseen-period validation, respectively. Results show that the proposed approach still had substantial predictive capability when applied to a new cultivation period. These results illustrate the potential of temporal-aware hybrid machine learning to achieve season-aware nutrient prediction and decision support in precision tomato cultivation.

Authors

Institutions

Publication Details

Journal
Applied Sciences
Published
2026-11-16
DOI
https://doi.org/10.3390/app162211354
Primary Topic
Smart Agriculture and AI
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Temporal-Aware Hybrid Machine Learning for Nutrient Prediction in Precision Tomato Cultivation

Padmapriya Arumugam, G. Yogeswari
5 links
Applied Sciences
Smart Agriculture and AI
article

Temporal-Aware Hybrid Machine Learning for Nutrient Prediction in Precision Tomato Cultivation

Padmapriya Arumugam, G. Yogeswari
article en

Abstract

Precise nutrient management strategies should consider the variability in crop growth and cultivation periods in precision agriculture. This paper proposes a temporal-aware hybrid machine learning approach based on Ridge Regression and Least-Squares Regression (LSR) for predicting soil nitrogen (N), phosphorus (P), and potassium (K) in precision tomato cultivation. The dataset comprises 180 observations collected over three cultivation periods, including soil, climate, and plant attributes. The proposed approach was evaluated using a standard random 80:20 train–test split and an unseen-period validation strategy to assess temporal generalization. The hybrid model produced an average R2 of 0.94 and 0.90 in the conventional and unseen-period validation, respectively. Results show that the proposed approach still had substantial predictive capability when applied to a new cultivation period. These results illustrate the potential of temporal-aware hybrid machine learning to achieve season-aware nutrient prediction and decision support in precision tomato cultivation.

Applied SciencesVol. 16(22)
Alagappa University (IN)
Alagappa University
Zero hunger
Smart Agriculture and AI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon