GRU–Transformer: A Novel Hybrid Model for Predicting Soil Moisture Content in Root Zones
The accurate measurement of soil moisture content emerges as a critical parameter within the ambit of agricultural irrigation management, wherein the precise prediction of this variable plays an instrumental role in enhancing the efficiency and conservation of agricultural water resources. This stud...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/14/3/432 |
| _version_ | 1827307428525375488 |
|---|---|
| author | Wengang Zheng Kai Zheng Lutao Gao Lili Zhangzhong Renping Lan Linlin Xu Jingxin Yu |
| author_facet | Wengang Zheng Kai Zheng Lutao Gao Lili Zhangzhong Renping Lan Linlin Xu Jingxin Yu |
| author_sort | Wengang Zheng |
| collection | DOAJ |
| description | The accurate measurement of soil moisture content emerges as a critical parameter within the ambit of agricultural irrigation management, wherein the precise prediction of this variable plays an instrumental role in enhancing the efficiency and conservation of agricultural water resources. This study introduces an innovative, cutting-edge hybrid model that ingeniously integrates Gated Recirculation Unit (GRU) and Transformer technologies, meticulously crafted to amplify the precision and reliability of soil moisture content forecasts. Leveraging meteorological and soil moisture datasets amassed from eight monitoring stations in Hebei Province, China, over the period from 2011 to 2018, this investigation thoroughly assesses the model’s efficacy against a diverse array of input variables and forecast durations. This assessment is concurrently contrasted with a range of conventional machine learning and deep learning frameworks. The results demonstrate that (1) the GRU–Transformer model exhibits remarkable superiority across various aspects, particularly in short-term projections (1- to 2-day latency). The model’s mean square error (MSE) for a 1-day forecast is notably low at 5.22%, reducing further to a significant 2.71%, while the mean coefficient of determination (R<sup>2</sup>) reaches a high of 89.92%. Despite a gradual increase in predictive error over extended forecast periods, the model consistently maintains robust performance. Moreover, the model shows exceptional versatility in managing different soil depths, notably excelling in predicting moisture levels at greater depths, thereby surpassing its performance in shallower soils. (2) The model’s predictive error inversely correlates with the reduction in parameters. Remarkably, with a streamlined set of just six soil moisture content parameters, the model predicts an average MSE of 0.59% and an R<sup>2</sup> of 98.86% for a three-day forecast, highlighting its resilience to varied parameter configurations. (3) In juxtaposition with prevalent models such as Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Gradient Boosting Decision Tree (GBDT), XGBoost, Random Forest, and deep learning models like Deep Neural Network (DNN), Convolutional Neural Network (CNN), and standalone GRU-branch and Transformer-branch models, the GRU–Transformer framework demonstrates a significant advantage in predicting soil moisture content with enhanced precision for a five-day forecast. This underscores its exceptional capacity to navigate the intricacies of soil moisture data. This research not only provides a potent decision-support tool for agricultural irrigation planning but also makes a substantial contribution to the field of water resource conservation and optimization in agriculture, while concurrently imparting novel insights into the application of deep learning techniques in the spheres of agricultural and environmental sciences. |
| first_indexed | 2024-04-24T18:38:58Z |
| format | Article |
| id | doaj.art-907fa04053584eafa5e3952cc02a7300 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-04-24T18:38:58Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-907fa04053584eafa5e3952cc02a73002024-03-27T13:16:31ZengMDPI AGAgronomy2073-43952024-02-0114343210.3390/agronomy14030432GRU–Transformer: A Novel Hybrid Model for Predicting Soil Moisture Content in Root ZonesWengang Zheng0Kai Zheng1Lutao Gao2Lili Zhangzhong3Renping Lan4Linlin Xu5Jingxin Yu6College of Agricultural Engineering, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Agricultural Engineering, Shanxi Agricultural University, Jinzhong 030801, ChinaSchool of Big Data, Yunnan Agricultural University, Kunming 650201, ChinaIntelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaIntelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaDepartment of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, CanadaIntelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaThe accurate measurement of soil moisture content emerges as a critical parameter within the ambit of agricultural irrigation management, wherein the precise prediction of this variable plays an instrumental role in enhancing the efficiency and conservation of agricultural water resources. This study introduces an innovative, cutting-edge hybrid model that ingeniously integrates Gated Recirculation Unit (GRU) and Transformer technologies, meticulously crafted to amplify the precision and reliability of soil moisture content forecasts. Leveraging meteorological and soil moisture datasets amassed from eight monitoring stations in Hebei Province, China, over the period from 2011 to 2018, this investigation thoroughly assesses the model’s efficacy against a diverse array of input variables and forecast durations. This assessment is concurrently contrasted with a range of conventional machine learning and deep learning frameworks. The results demonstrate that (1) the GRU–Transformer model exhibits remarkable superiority across various aspects, particularly in short-term projections (1- to 2-day latency). The model’s mean square error (MSE) for a 1-day forecast is notably low at 5.22%, reducing further to a significant 2.71%, while the mean coefficient of determination (R<sup>2</sup>) reaches a high of 89.92%. Despite a gradual increase in predictive error over extended forecast periods, the model consistently maintains robust performance. Moreover, the model shows exceptional versatility in managing different soil depths, notably excelling in predicting moisture levels at greater depths, thereby surpassing its performance in shallower soils. (2) The model’s predictive error inversely correlates with the reduction in parameters. Remarkably, with a streamlined set of just six soil moisture content parameters, the model predicts an average MSE of 0.59% and an R<sup>2</sup> of 98.86% for a three-day forecast, highlighting its resilience to varied parameter configurations. (3) In juxtaposition with prevalent models such as Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Gradient Boosting Decision Tree (GBDT), XGBoost, Random Forest, and deep learning models like Deep Neural Network (DNN), Convolutional Neural Network (CNN), and standalone GRU-branch and Transformer-branch models, the GRU–Transformer framework demonstrates a significant advantage in predicting soil moisture content with enhanced precision for a five-day forecast. This underscores its exceptional capacity to navigate the intricacies of soil moisture data. This research not only provides a potent decision-support tool for agricultural irrigation planning but also makes a substantial contribution to the field of water resource conservation and optimization in agriculture, while concurrently imparting novel insights into the application of deep learning techniques in the spheres of agricultural and environmental sciences.https://www.mdpi.com/2073-4395/14/3/432GRUtransformersoil moisture contentdeep learning |
| spellingShingle | Wengang Zheng Kai Zheng Lutao Gao Lili Zhangzhong Renping Lan Linlin Xu Jingxin Yu GRU–Transformer: A Novel Hybrid Model for Predicting Soil Moisture Content in Root Zones Agronomy GRU transformer soil moisture content deep learning |
| title | GRU–Transformer: A Novel Hybrid Model for Predicting Soil Moisture Content in Root Zones |
| title_full | GRU–Transformer: A Novel Hybrid Model for Predicting Soil Moisture Content in Root Zones |
| title_fullStr | GRU–Transformer: A Novel Hybrid Model for Predicting Soil Moisture Content in Root Zones |
| title_full_unstemmed | GRU–Transformer: A Novel Hybrid Model for Predicting Soil Moisture Content in Root Zones |
| title_short | GRU–Transformer: A Novel Hybrid Model for Predicting Soil Moisture Content in Root Zones |
| title_sort | gru transformer a novel hybrid model for predicting soil moisture content in root zones |
| topic | GRU transformer soil moisture content deep learning |
| url | https://www.mdpi.com/2073-4395/14/3/432 |
| work_keys_str_mv | AT wengangzheng grutransformeranovelhybridmodelforpredictingsoilmoisturecontentinrootzones AT kaizheng grutransformeranovelhybridmodelforpredictingsoilmoisturecontentinrootzones AT lutaogao grutransformeranovelhybridmodelforpredictingsoilmoisturecontentinrootzones AT lilizhangzhong grutransformeranovelhybridmodelforpredictingsoilmoisturecontentinrootzones AT renpinglan grutransformeranovelhybridmodelforpredictingsoilmoisturecontentinrootzones AT linlinxu grutransformeranovelhybridmodelforpredictingsoilmoisturecontentinrootzones AT jingxinyu grutransformeranovelhybridmodelforpredictingsoilmoisturecontentinrootzones |