Multimodal sequential cross-modal transformer for predicting plant available water capacity (PAWC) from time series of weather and crop biological data
Deep learning (DL) and machine learning (ML) have been applied widely to satellite data of vegetation indices to infer indirect features associated with soil characteristics that affect crop performance in rain-fed environments. In this paper, we propose a DL model for prediction of plant available...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Agricultural Water Management |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0378377424004608 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841557040678305792 |
|---|---|
| author | Dung Nguyen Peter de Voil Andries Potgieter Yash P. Dang Thomas G. Orton Duc Thanh Nguyen Thanh Thi Nguyen Scott C. Chapman |
| author_facet | Dung Nguyen Peter de Voil Andries Potgieter Yash P. Dang Thomas G. Orton Duc Thanh Nguyen Thanh Thi Nguyen Scott C. Chapman |
| author_sort | Dung Nguyen |
| collection | DOAJ |
| description | Deep learning (DL) and machine learning (ML) have been applied widely to satellite data of vegetation indices to infer indirect features associated with soil characteristics that affect crop performance in rain-fed environments. In this paper, we propose a DL model for prediction of plant available water capacity (PAWC) of the soil from sequential multi-modal data including time series of biomass, leaf area index (LAI), normalised difference vegetation index (NDVI), and cumulative weather variables. By initiating large numbers of simulations with different soil PAWC, weather and management parameters, we explore combinations of the simulation outputs and the weather to estimate the PAWC and to determine the factors that impede the accuracy of the prediction model. Experimental results demonstrate the significant potential of our method compared with traditional ML methods. Specifically, our method increases the prediction accuracy in situations where each PAWC profile is grouped into two or five classes of PAWC. For more classes (10 classes), the model achieves more than 60% for the overall accuracy and performs well on the lowest five PAWC classes. The utilisation of sequential multi-modal data to predict soil water level provides a direction for future work to translate onto empirical datasets and also to explore the boundaries of the prediction ability of DL models. |
| format | Article |
| id | doaj-art-bce52efb486843d89f5c6a3944df5812 |
| institution | Kabale University |
| issn | 1873-2283 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Agricultural Water Management |
| spelling | doaj-art-bce52efb486843d89f5c6a3944df58122025-01-07T04:16:40ZengElsevierAgricultural Water Management1873-22832025-02-01307109124Multimodal sequential cross-modal transformer for predicting plant available water capacity (PAWC) from time series of weather and crop biological dataDung Nguyen0Peter de Voil1Andries Potgieter2Yash P. Dang3Thomas G. Orton4Duc Thanh Nguyen5Thanh Thi Nguyen6Scott C. Chapman7The University of Queensland, Queensland Alliance for Agriculture and Food Innovation Gatton, QLD, 4343, Australia; The University of Queensland, School of Agriculture and Food Sustainability, Gatton, QLD, 4343, Australia; Correspondence to: 195 Carmody Road, St Lucia, QLD, 4067, Australia.The University of Queensland, Queensland Alliance for Agriculture and Food Innovation Gatton, QLD, 4343, AustraliaThe University of Queensland, Queensland Alliance for Agriculture and Food Innovation Gatton, QLD, 4343, AustraliaThe University of Queensland, School of Agriculture and Food Sustainability, Gatton, QLD, 4343, AustraliaThe University of Queensland, School of Agriculture and Food Sustainability, Gatton, QLD, 4343, AustraliaDeakin University, School of Information Technology, Geelong, Victoria, 3216, AustraliaDeakin University, School of Information Technology, Geelong, Victoria, 3216, AustraliaThe University of Queensland, School of Agriculture and Food Sustainability, Gatton, QLD, 4343, AustraliaDeep learning (DL) and machine learning (ML) have been applied widely to satellite data of vegetation indices to infer indirect features associated with soil characteristics that affect crop performance in rain-fed environments. In this paper, we propose a DL model for prediction of plant available water capacity (PAWC) of the soil from sequential multi-modal data including time series of biomass, leaf area index (LAI), normalised difference vegetation index (NDVI), and cumulative weather variables. By initiating large numbers of simulations with different soil PAWC, weather and management parameters, we explore combinations of the simulation outputs and the weather to estimate the PAWC and to determine the factors that impede the accuracy of the prediction model. Experimental results demonstrate the significant potential of our method compared with traditional ML methods. Specifically, our method increases the prediction accuracy in situations where each PAWC profile is grouped into two or five classes of PAWC. For more classes (10 classes), the model achieves more than 60% for the overall accuracy and performs well on the lowest five PAWC classes. The utilisation of sequential multi-modal data to predict soil water level provides a direction for future work to translate onto empirical datasets and also to explore the boundaries of the prediction ability of DL models.http://www.sciencedirect.com/science/article/pii/S0378377424004608Cross-modal attentionTransformerMachine learningAPSIMSoilPlant |
| spellingShingle | Dung Nguyen Peter de Voil Andries Potgieter Yash P. Dang Thomas G. Orton Duc Thanh Nguyen Thanh Thi Nguyen Scott C. Chapman Multimodal sequential cross-modal transformer for predicting plant available water capacity (PAWC) from time series of weather and crop biological data Agricultural Water Management Cross-modal attention Transformer Machine learning APSIM Soil Plant |
| title | Multimodal sequential cross-modal transformer for predicting plant available water capacity (PAWC) from time series of weather and crop biological data |
| title_full | Multimodal sequential cross-modal transformer for predicting plant available water capacity (PAWC) from time series of weather and crop biological data |
| title_fullStr | Multimodal sequential cross-modal transformer for predicting plant available water capacity (PAWC) from time series of weather and crop biological data |
| title_full_unstemmed | Multimodal sequential cross-modal transformer for predicting plant available water capacity (PAWC) from time series of weather and crop biological data |
| title_short | Multimodal sequential cross-modal transformer for predicting plant available water capacity (PAWC) from time series of weather and crop biological data |
| title_sort | multimodal sequential cross modal transformer for predicting plant available water capacity pawc from time series of weather and crop biological data |
| topic | Cross-modal attention Transformer Machine learning APSIM Soil Plant |
| url | http://www.sciencedirect.com/science/article/pii/S0378377424004608 |
| work_keys_str_mv | AT dungnguyen multimodalsequentialcrossmodaltransformerforpredictingplantavailablewatercapacitypawcfromtimeseriesofweatherandcropbiologicaldata AT peterdevoil multimodalsequentialcrossmodaltransformerforpredictingplantavailablewatercapacitypawcfromtimeseriesofweatherandcropbiologicaldata AT andriespotgieter multimodalsequentialcrossmodaltransformerforpredictingplantavailablewatercapacitypawcfromtimeseriesofweatherandcropbiologicaldata AT yashpdang multimodalsequentialcrossmodaltransformerforpredictingplantavailablewatercapacitypawcfromtimeseriesofweatherandcropbiologicaldata AT thomasgorton multimodalsequentialcrossmodaltransformerforpredictingplantavailablewatercapacitypawcfromtimeseriesofweatherandcropbiologicaldata AT ducthanhnguyen multimodalsequentialcrossmodaltransformerforpredictingplantavailablewatercapacitypawcfromtimeseriesofweatherandcropbiologicaldata AT thanhthinguyen multimodalsequentialcrossmodaltransformerforpredictingplantavailablewatercapacitypawcfromtimeseriesofweatherandcropbiologicaldata AT scottcchapman multimodalsequentialcrossmodaltransformerforpredictingplantavailablewatercapacitypawcfromtimeseriesofweatherandcropbiologicaldata |