Predicting Irrigated Rice Soil–Water Conditions Using Multispectral Remote Sensing and Machine Learning in Semi-Arid Australia.
Saved in:
| Title: | Predicting Irrigated Rice Soil–Water Conditions Using Multispectral Remote Sensing and Machine Learning in Semi-Arid Australia. |
|---|---|
| Authors: | Tondato, Brenno1 (AUTHOR) b.tondato@deakin.edu.au, Tercete, Gustavo1 (AUTHOR), Maia, Rodrigo Filev1 (AUTHOR), Hornbuckle, John1 (AUTHOR) |
| Source: | Remote Sensing. Aug2026, Vol. 18 Issue 15, p2504. 27p. |
| Subjects: | Multispectral imaging, Machine learning, Irrigation management, Irrigation efficiency, Arid regions, Soil moisture, Rice farming, Vegetation greenness |
| Geographic Terms: | Australia |
| Abstract: | Highlights: What are the main findings? Remote sensing bands A R V I , W e t n e s s , P S R I , P S R I 2 , S T R , G V M I and V S D I were the most informative of the 156 remote sensing features identified in the literature. However, soil–water condition predictions are mainly driven by vegetation-sensitive indices of A R V I , P S R I 2 , a n d G V M I . The "Saturated" and "Dry" soil–water conditions were mostly accurately predicted during the initial and final rice growing stages, with a predominance of "Flooded" predictions during the late vegetative and reproductive stages. What are the implications of the main findings? Selected multi-spectral remote sensing indices represent a set of features that encode information about different soil–water conditions in irrigated rice and can be used in irrigation management applications. The model could be used as a retrospective diagnostic tool at different water levels in the initial and final stages, as well as to support conservative irrigation practices. Further investigation is required to improve predictions during late vegetative and reproductive stages when considering water-saving irrigation practices. Detecting soil–water conditions ranging from dry to fully ponded in rice fields using solely multispectral remote sensing is crucial for irrigation water management practices focused on water savings in Semi-Arid Australia. To this end, this research employed the Minimum Redundancy Maximum Relevance (mRMR) algorithm to identify a set of multispectral remote sensing indices for use with Machine Learning (ML) to predict three soil–water conditions in irrigated rice: "Flooded", "Saturated", and "Dry". Two models were developed: Model 1, using the most frequently used remote sensing indices in the literature; Model 2, including multispectral variables selected by the mRMR algorithm. Model 2 achieved the highest performance, with an accuracy of 0.64 and a k a p p a of 0.46, and ROC-AUC values of 0.87, 0.62, and 0.83 for "Flooded", "Saturated", and "Dry", respectively. All models exhibit high confusion rates between "Flooded" and "Saturated" conditions, suggesting that multispectral remote sensing doesn't provide sufficient information to distinguish these soil–water conditions. The SHAP analysis revealed that vegetation-sensitive indices encoding information on crop biomass, plant moisture, and senescence status were the primary drivers of soil–water condition prediction. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 196272184 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Predicting Irrigated Rice Soil–Water Conditions Using Multispectral Remote Sensing and Machine Learning in Semi-Arid Australia. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Tondato%2C+Brenno%22">Tondato, Brenno</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> b.tondato@deakin.edu.au</i><br /><searchLink fieldCode="AR" term="%22Tercete%2C+Gustavo%22">Tercete, Gustavo</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Maia%2C+Rodrigo+Filev%22">Maia, Rodrigo Filev</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hornbuckle%2C+John%22">Hornbuckle, John</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Aug2026, Vol. 18 Issue 15, p2504. 27p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Multispectral+imaging%22">Multispectral imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Irrigation+management%22">Irrigation management</searchLink><br /><searchLink fieldCode="DE" term="%22Irrigation+efficiency%22">Irrigation efficiency</searchLink><br /><searchLink fieldCode="DE" term="%22Arid+regions%22">Arid regions</searchLink><br /><searchLink fieldCode="DE" term="%22Soil+moisture%22">Soil moisture</searchLink><br /><searchLink fieldCode="DE" term="%22Rice+farming%22">Rice farming</searchLink><br /><searchLink fieldCode="DE" term="%22Vegetation+greenness%22">Vegetation greenness</searchLink> – Name: SubjectGeographic Label: Geographic Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Australia%22">Australia</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? Remote sensing bands A R V I ,   W e t n e s s ,   P S R I ,   P S R I 2 ,   S T R ,   G V M I and V S D I were the most informative of the 156 remote sensing features identified in the literature. However, soil–water condition predictions are mainly driven by vegetation-sensitive indices of A R V I ,  P S R I 2 ,   a n d   G V M I . The "Saturated" and "Dry" soil–water conditions were mostly accurately predicted during the initial and final rice growing stages, with a predominance of "Flooded" predictions during the late vegetative and reproductive stages. What are the implications of the main findings? Selected multi-spectral remote sensing indices represent a set of features that encode information about different soil–water conditions in irrigated rice and can be used in irrigation management applications. The model could be used as a retrospective diagnostic tool at different water levels in the initial and final stages, as well as to support conservative irrigation practices. Further investigation is required to improve predictions during late vegetative and reproductive stages when considering water-saving irrigation practices. Detecting soil–water conditions ranging from dry to fully ponded in rice fields using solely multispectral remote sensing is crucial for irrigation water management practices focused on water savings in Semi-Arid Australia. To this end, this research employed the Minimum Redundancy Maximum Relevance (mRMR) algorithm to identify a set of multispectral remote sensing indices for use with Machine Learning (ML) to predict three soil–water conditions in irrigated rice: "Flooded", "Saturated", and "Dry". Two models were developed: Model 1, using the most frequently used remote sensing indices in the literature; Model 2, including multispectral variables selected by the mRMR algorithm. Model 2 achieved the highest performance, with an accuracy of 0.64 and a k a p p a of 0.46, and ROC-AUC values of 0.87, 0.62, and 0.83 for "Flooded", "Saturated", and "Dry", respectively. All models exhibit high confusion rates between "Flooded" and "Saturated" conditions, suggesting that multispectral remote sensing doesn't provide sufficient information to distinguish these soil–water conditions. The SHAP analysis revealed that vegetation-sensitive indices encoding information on crop biomass, plant moisture, and senescence status were the primary drivers of soil–water condition prediction. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=196272184 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs18152504 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 27 StartPage: 2504 Subjects: – SubjectFull: Multispectral imaging Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Irrigation management Type: general – SubjectFull: Irrigation efficiency Type: general – SubjectFull: Arid regions Type: general – SubjectFull: Soil moisture Type: general – SubjectFull: Rice farming Type: general – SubjectFull: Vegetation greenness Type: general – SubjectFull: Australia Type: general Titles: – TitleFull: Predicting Irrigated Rice Soil–Water Conditions Using Multispectral Remote Sensing and Machine Learning in Semi-Arid Australia. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Tondato, Brenno – PersonEntity: Name: NameFull: Tercete, Gustavo – PersonEntity: Name: NameFull: Maia, Rodrigo Filev – PersonEntity: Name: NameFull: Hornbuckle, John IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 08 Text: Aug2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 18 – Type: issue Value: 15 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
