Enhancing the prediction of irrigation demand for open field vegetable crops in Germany through neural networks, transfer learning, and ensemble models

Precise irrigation management in vegetable production is key for optimizing water use and ensuring crop productivity. This study develops two types of artificial neural networks (ANNs), multilayer perceptron (MLPs) and long short-term memory (LSTM) networks for the prediction of available water capa...

Full description

Saved in:
Bibliographic Details
Main Authors: Samantha Rubo, Jana Zinkernagel
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Agricultural Water Management
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0378377425001167
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850146636818284544
author Samantha Rubo
Jana Zinkernagel
author_facet Samantha Rubo
Jana Zinkernagel
author_sort Samantha Rubo
collection DOAJ
description Precise irrigation management in vegetable production is key for optimizing water use and ensuring crop productivity. This study develops two types of artificial neural networks (ANNs), multilayer perceptron (MLPs) and long short-term memory (LSTM) networks for the prediction of available water capacity (AWC in %) as target parameter for irrigation scheduling. These ANNs are trained with experimental data from three-year (2020–2023) open field trials with spinach on two sites in Germany, and for three soil layers (0–20 cm, 20–40 cm and 40–60 cm). This data encompassed soil texture, plant signals and plant developmental status derived from vegetation indices based on spectral reflectance along with meteorological variables including mean air temperature, humidity, wind speed, photothermal time, and their cumulative values. Two additional models are pretrained with freely accessible AWC data from 320 stations across Germany and subsequently fine-tuned with the same experimental data as before. An ANN ensemble model consolidates the knowledge from preceding models to enhance robustness and promote transferability to new climatic conditions and soil textures. Methods of explainable AI such as variable importance analysis and sensitivity analysis enhance the model explainability by identifying influential factors for each soil layer. Models trained with additional AWC data and fine-tuned with experimental performed best (R2 > 0.98, RMSE <1.5 %) across all soil depths. The LSTM models perform slightly better than the MLP equivalent, emphasizing the importance of temporal dependencies in soil moisture prediction. The ensemble model minimized cumulative errors and provided stable results by averaging the outputs of all models. While ANNs provide highly accurate results, implementation requires expertise and resources of IT infrastructures such as the development of interfaces to weather stations and, if applicable, additional sensors. Consequently, deploying the ANN-based IS in practice requires a service provider with specialized knowledge in both IT and vegetable production for effective implementation and maintenance.
format Article
id doaj-art-e4e25e81842f4302837868797e0f2572
institution OA Journals
issn 1873-2283
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series Agricultural Water Management
spelling doaj-art-e4e25e81842f4302837868797e0f25722025-08-20T02:27:47ZengElsevierAgricultural Water Management1873-22832025-05-0131210940210.1016/j.agwat.2025.109402Enhancing the prediction of irrigation demand for open field vegetable crops in Germany through neural networks, transfer learning, and ensemble modelsSamantha Rubo0Jana Zinkernagel1Department of Vegetable Crops, Hochschule Geisenheim University, Von-Lade-Str. 1, Geisenheim 65366, GermanyCorresponding author.; Department of Vegetable Crops, Hochschule Geisenheim University, Von-Lade-Str. 1, Geisenheim 65366, GermanyPrecise irrigation management in vegetable production is key for optimizing water use and ensuring crop productivity. This study develops two types of artificial neural networks (ANNs), multilayer perceptron (MLPs) and long short-term memory (LSTM) networks for the prediction of available water capacity (AWC in %) as target parameter for irrigation scheduling. These ANNs are trained with experimental data from three-year (2020–2023) open field trials with spinach on two sites in Germany, and for three soil layers (0–20 cm, 20–40 cm and 40–60 cm). This data encompassed soil texture, plant signals and plant developmental status derived from vegetation indices based on spectral reflectance along with meteorological variables including mean air temperature, humidity, wind speed, photothermal time, and their cumulative values. Two additional models are pretrained with freely accessible AWC data from 320 stations across Germany and subsequently fine-tuned with the same experimental data as before. An ANN ensemble model consolidates the knowledge from preceding models to enhance robustness and promote transferability to new climatic conditions and soil textures. Methods of explainable AI such as variable importance analysis and sensitivity analysis enhance the model explainability by identifying influential factors for each soil layer. Models trained with additional AWC data and fine-tuned with experimental performed best (R2 > 0.98, RMSE <1.5 %) across all soil depths. The LSTM models perform slightly better than the MLP equivalent, emphasizing the importance of temporal dependencies in soil moisture prediction. The ensemble model minimized cumulative errors and provided stable results by averaging the outputs of all models. While ANNs provide highly accurate results, implementation requires expertise and resources of IT infrastructures such as the development of interfaces to weather stations and, if applicable, additional sensors. Consequently, deploying the ANN-based IS in practice requires a service provider with specialized knowledge in both IT and vegetable production for effective implementation and maintenance.http://www.sciencedirect.com/science/article/pii/S0378377425001167Irrigation demand modelIrrigation schedulingSoil moistureRoot mean square errorNeural network ensemble
spellingShingle Samantha Rubo
Jana Zinkernagel
Enhancing the prediction of irrigation demand for open field vegetable crops in Germany through neural networks, transfer learning, and ensemble models
Agricultural Water Management
Irrigation demand model
Irrigation scheduling
Soil moisture
Root mean square error
Neural network ensemble
title Enhancing the prediction of irrigation demand for open field vegetable crops in Germany through neural networks, transfer learning, and ensemble models
title_full Enhancing the prediction of irrigation demand for open field vegetable crops in Germany through neural networks, transfer learning, and ensemble models
title_fullStr Enhancing the prediction of irrigation demand for open field vegetable crops in Germany through neural networks, transfer learning, and ensemble models
title_full_unstemmed Enhancing the prediction of irrigation demand for open field vegetable crops in Germany through neural networks, transfer learning, and ensemble models
title_short Enhancing the prediction of irrigation demand for open field vegetable crops in Germany through neural networks, transfer learning, and ensemble models
title_sort enhancing the prediction of irrigation demand for open field vegetable crops in germany through neural networks transfer learning and ensemble models
topic Irrigation demand model
Irrigation scheduling
Soil moisture
Root mean square error
Neural network ensemble
url http://www.sciencedirect.com/science/article/pii/S0378377425001167
work_keys_str_mv AT samantharubo enhancingthepredictionofirrigationdemandforopenfieldvegetablecropsingermanythroughneuralnetworkstransferlearningandensemblemodels
AT janazinkernagel enhancingthepredictionofirrigationdemandforopenfieldvegetablecropsingermanythroughneuralnetworkstransferlearningandensemblemodels