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...
Saved in:
| Main Authors: | , |
|---|---|
| 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 |