Hybrid machine learning and physics-based model for estimating lettuce (Lactuca sativa) growth and resource consumption in aeroponic systems - research article overview

Aug 5, 2026

Global population growth and environmental degradation make agricultural production and resource management increasingly complex, especially as traditional farming struggles to optimize nutrient and water delivery while maintaining product quality. This study develops a hybrid predictive framework that integrates machine learning with a physics-based model to estimate lettuce fresh weight, leaf area, nitrate levels, and water consumption in aeroponic systems. Validation with real-time aeroponic data shows strong performance for fresh weight and total leaf area, while nitrate and water predictions are less accurate due to limited training data and constraints of the physics component under soilless conditions. The approach supports more efficient, sustainable controlled environment agriculture.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Motivation and context

Challenges in agriculture and food security

Controlled Environment Agriculture (CEA)

Role of IoT in controlled environments

Aeroponic systems and rationale

Aeroponics advantages for water and nutrient control

Hybrid modeling approach

Physics-based model + machine learning integration

Dynamic hybrid framework

Data validation and results

Predictive performance for growth and quality traits

Limitations for nitrate and water estimates

POLITECNICO DI TORINO Repository ISTITUZIONALE Hybrid machine learning and physics-based model for estimating lettuce (Lactuca sativa) growth and resource consumption in aeroponic systems Original Hybrid machine learning and physics-based model for estimating lettuce (Lactuca sativa) growth and resource consumption in aeroponic systems / Fasciolo, Benedetta; Grasso, Nicolo'; Bruno, Giulia; Chiabert, Paolo. -In: SCIENTIFIC REPORTS. -ISSN 2045-2322. -ELETTRONICO. -15:1(2025) . [10 . 1038/s41598-025-02763-9] Availability: This version is available at: 11583/3001523 since: 2025-07-03T13:33:41Z Publisher: springer nature Published DOI:10.1038/s41598-025-02763-9 Terms of use: This article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository Publisher copyright (Article begins on next page) 04 October 2025 [www. nature.com/scientificreports](www. nature.com/scientificreports) OPEN Hybrid machine learning and physics-based model for estimating lettuce (Lactuca sativa) growth and resource consumption in aeroponicsystems Benedetta Fasciolo􀀍, Nicolò Grasso, Giulia Bruno & Paolo Chiabert As the global population is expected to reach 10.3 billion by the mid-2080s, optimizing agricultural production and resource management is crucial. Climate change and environmental degradation further complicate these challenges, impacting crop productivity and food security. Traditional farming methods struggle with efficiently managing nutrients and water while ensuring high-quality products, leading to resource wastage and food safety concerns. This study aims to develop a hybrid model combining machine learning and physics-based techniques to predict fresh weight, leaf area, nitrate levels, and water consumption in lettuce grown in aeroponic systems, thereby enhancing resource management and product quality. We integrated a physics-based model with machine learning algorithms to create a dynamic hybrid framework. The model was validated with real-time data from aeroponic systems, showing good predictive performance, particularly for fresh weight and total leaf area. In contrast, predictions of nitrate content and water consumption were less accurate, due in part to smaller training datasets and limitations of the physics-based component under soilless conditions. Despite these challenges, the hybrid model offers a promising solution for optimizing controlled environment agriculture, addressing critical challenges in modern agriculture by improving efficiency and sustainability. Keywords Hybrid model, Machine learning, Physics-based model, Aeroponic, IoT, Predictive model Optimizing resources and agricultural production is crucial to addressing the growing global population and urbanization challenges. The world population will grow over the next sixty years from 8.2 billion in 2024 to around 10.3 billion people in the mid-2080s1. A significant increase in agricultural production will be required in the coming decades to ensure food security. However, growing urbanization and the environmental crisis pose significant threats. Climate change strongly impacts plant abiotic stress, such as high temperatures2, salinity3, and heavy metals4, compromising agricultural productivity. Moreover, the limited availability of essential resources like macro and micronutrients5 and soil pH variations further exacerbate the situation4. On the other hand, agricultural activities like deforestation6 and intensive use of fertilizers and pesticides7,8 contribute to the environmental crisis by reducing the soil organic carbon pool and causing water and air pollution. Food waste is another critical issue with significant environmental and food security implications. Approximately 14% of all food produced is estimated to be lost between the post-harvest stage and just before the retail stage9. Developing more efficient agricultural practices and adopting innovat

FAQs

What is the main goal of the hybrid model described in the document?

To predict lettuce growth metrics and key resource consumption variables in aeroponic systems by combining machine learning with a physics-based model.

Which outputs are predicted using the hybrid framework?

Fresh weight, leaf area, nitrate levels, and water consumption for lettuce (Lactuca sativa) grown aeroponically.

How does the model perform, and what limits its accuracy?

It performs well for fresh weight and total leaf area, while nitrate content and water consumption are less accurate due to smaller training datasets and limitations of the physics-based component under soilless conditions.

Aug 5, 2026

Upload by Seraphina