View in EDS HTML Full Text PDF Full Text

Evaluating the Performance of AlphaEarth Foundation Embeddings for Irrigated Cropland Mapping Across Regions and Years.

Saved in:
Bibliographic Details
Title: Evaluating the Performance of AlphaEarth Foundation Embeddings for Irrigated Cropland Mapping Across Regions and Years.
Authors: Yang, Lulu1 (AUTHOR), Gao, Yuan1,2 (AUTHOR), Zhao, Xiangyang1,3 (AUTHOR), Liang, Nannan1,4 (AUTHOR), Ma, Ru1 (AUTHOR), Xi, Shixiang1,2 (AUTHOR), Zhang, Xiao2,3 (AUTHOR), Wang, Rui1,4 (AUTHOR) rico@nwafu.edu.cn
Source: Remote Sensing. Apr2026, Vol. 18 Issue 7, p1065. 24p.
Subjects: Agricultural water supply, Land use mapping, Classification algorithms, DeepMind Technologies Ltd., Remote sensing, Remote-sensing images, Machine learning, Spatiotemporal processes
Geographic Terms: China, United States, Kansas
Abstract: Highlights: What are the main findings? This study presents the first systematic assessment of AEF embeddings for irrigated cropland mapping. AEF outperforms conventional optical and SAR predictors, achieving an overall accuracy of 96.2% and a maximum Jeffries–Matusita (JM) distance of 1.58 (A29). What are the implications of the main findings? AEF demonstrates stable cross-year transferability (OA > 0.87) but shows limited generalization across regions. A single AEF embedding (A29) provides parcel-scale separability comparable to commonly used vegetation and moisture indices. Accurate irrigated cropland mapping is critical for agricultural water management and food security. Existing image-based irrigation mapping workflows primarily rely on vegetation indices and synthetic aperture radar (SAR) backscatter features, which have limited capacity to characterize the temporal evolution of irrigation processes and crop growth conditions. The AlphaEarth Foundation (AEF) model developed by Google DeepMind provides compact embeddings with temporal semantic information learned via self-supervision, yet their utility for irrigation mapping has not been systematically assessed. In this study, a comprehensive assessment of AEF embeddings for irrigated cropland mapping was performed in terms of feature separability, classification performance, and spatiotemporal transferability. Experiments were conducted in two representative irrigated regions: the Guanzhong Plain in China and Kansas in the USA. Class separability of the 64 embedding dimensions was quantified using the Jeffries–Matusita (JM) distance. Then, the AEF embeddings were compared with the Sentinel feature set (Sentinel-2 bands, normalized difference vegetation index(NDVI), enhanced vegetation index(EVI), normalized difference water index(NDWI) and Sentinel-1 vertical transmit vertical receive(VV), vertical transmit horizontal receive(VH)) using K-means clustering and supervised classifiers, including Decision Tree (DT), Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Support Vector Machine (SVM), and Multi-layer Perceptron (MLP). Finally, transfer experiments across 2022 and 2024 in the Guanzhong Plain and Kansas were conducted to examine cross-year and cross-region performance. The results showed that AEF embeddings consistently provide stronger class separability in both study areas, with a maximum JM distance of 1.58 (A29). Using AEF embeddings, RF achieved overall accuracies (OA) of 0.95 in the Guanzhong Plain and 0.93 in Kansas, outperforming models based on Sentinel-1/2 bands and indices. Notably, unsupervised K-means clustering on AEF embeddings yielded OA > 0.85, indicating high intrinsic separability between irrigated and rainfed croplands. Transfer experiments further demonstrate stable temporal transfer (cross-year OA > 0.87), whereas cross-region transfer is constrained by differences in irrigation regimes, crop phenology and management practices, resulting in limited spatial generalization (OA~0.3). Overall, this study demonstrates the potential of high-information-density representations from geospatial foundation models for irrigated cropland mapping and provides methodological and technical insights to support transfer learning and operational mapping over large areas. [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.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 192958600
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Evaluating the Performance of AlphaEarth Foundation Embeddings for Irrigated Cropland Mapping Across Regions and Years.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yang%2C+Lulu%22">Yang, Lulu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gao%2C+Yuan%22">Gao, Yuan</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhao%2C+Xiangyang%22">Zhao, Xiangyang</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liang%2C+Nannan%22">Liang, Nannan</searchLink><relatesTo>1,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ma%2C+Ru%22">Ma, Ru</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xi%2C+Shixiang%22">Xi, Shixiang</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Xiao%22">Zhang, Xiao</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Rui%22">Wang, Rui</searchLink><relatesTo>1,4</relatesTo> (AUTHOR)<i> rico@nwafu.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Apr2026, Vol. 18 Issue 7, p1065. 24p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Agricultural+water+supply%22">Agricultural water supply</searchLink><br /><searchLink fieldCode="DE" term="%22Land+use+mapping%22">Land use mapping</searchLink><br /><searchLink fieldCode="DE" term="%22Classification+algorithms%22">Classification algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22DeepMind+Technologies+Ltd%2E%22">DeepMind Technologies Ltd.</searchLink><br /><searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Remote-sensing+images%22">Remote-sensing images</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Spatiotemporal+processes%22">Spatiotemporal processes</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22China%22">China</searchLink><br /><searchLink fieldCode="DE" term="%22United+States%22">United States</searchLink><br /><searchLink fieldCode="DE" term="%22Kansas%22">Kansas</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Highlights: What are the main findings? This study presents the first systematic assessment of AEF embeddings for irrigated cropland mapping. AEF outperforms conventional optical and SAR predictors, achieving an overall accuracy of 96.2% and a maximum Jeffries–Matusita (JM) distance of 1.58 (A29). What are the implications of the main findings? AEF demonstrates stable cross-year transferability (OA > 0.87) but shows limited generalization across regions. A single AEF embedding (A29) provides parcel-scale separability comparable to commonly used vegetation and moisture indices. Accurate irrigated cropland mapping is critical for agricultural water management and food security. Existing image-based irrigation mapping workflows primarily rely on vegetation indices and synthetic aperture radar (SAR) backscatter features, which have limited capacity to characterize the temporal evolution of irrigation processes and crop growth conditions. The AlphaEarth Foundation (AEF) model developed by Google DeepMind provides compact embeddings with temporal semantic information learned via self-supervision, yet their utility for irrigation mapping has not been systematically assessed. In this study, a comprehensive assessment of AEF embeddings for irrigated cropland mapping was performed in terms of feature separability, classification performance, and spatiotemporal transferability. Experiments were conducted in two representative irrigated regions: the Guanzhong Plain in China and Kansas in the USA. Class separability of the 64 embedding dimensions was quantified using the Jeffries–Matusita (JM) distance. Then, the AEF embeddings were compared with the Sentinel feature set (Sentinel-2 bands, normalized difference vegetation index(NDVI), enhanced vegetation index(EVI), normalized difference water index(NDWI) and Sentinel-1 vertical transmit vertical receive(VV), vertical transmit horizontal receive(VH)) using K-means clustering and supervised classifiers, including Decision Tree (DT), Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Support Vector Machine (SVM), and Multi-layer Perceptron (MLP). Finally, transfer experiments across 2022 and 2024 in the Guanzhong Plain and Kansas were conducted to examine cross-year and cross-region performance. The results showed that AEF embeddings consistently provide stronger class separability in both study areas, with a maximum JM distance of 1.58 (A29). Using AEF embeddings, RF achieved overall accuracies (OA) of 0.95 in the Guanzhong Plain and 0.93 in Kansas, outperforming models based on Sentinel-1/2 bands and indices. Notably, unsupervised K-means clustering on AEF embeddings yielded OA > 0.85, indicating high intrinsic separability between irrigated and rainfed croplands. Transfer experiments further demonstrate stable temporal transfer (cross-year OA > 0.87), whereas cross-region transfer is constrained by differences in irrigation regimes, crop phenology and management practices, resulting in limited spatial generalization (OA~0.3). Overall, this study demonstrates the potential of high-information-density representations from geospatial foundation models for irrigated cropland mapping and provides methodological and technical insights to support transfer learning and operational mapping over large areas. [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=192958600
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs18071065
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 1065
    Subjects:
      – SubjectFull: Agricultural water supply
        Type: general
      – SubjectFull: Land use mapping
        Type: general
      – SubjectFull: Classification algorithms
        Type: general
      – SubjectFull: DeepMind Technologies Ltd.
        Type: general
      – SubjectFull: Remote sensing
        Type: general
      – SubjectFull: Remote-sensing images
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Spatiotemporal processes
        Type: general
      – SubjectFull: China
        Type: general
      – SubjectFull: United States
        Type: general
      – SubjectFull: Kansas
        Type: general
    Titles:
      – TitleFull: Evaluating the Performance of AlphaEarth Foundation Embeddings for Irrigated Cropland Mapping Across Regions and Years.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yang, Lulu
      – PersonEntity:
          Name:
            NameFull: Gao, Yuan
      – PersonEntity:
          Name:
            NameFull: Zhao, Xiangyang
      – PersonEntity:
          Name:
            NameFull: Liang, Nannan
      – PersonEntity:
          Name:
            NameFull: Ma, Ru
      – PersonEntity:
          Name:
            NameFull: Xi, Shixiang
      – PersonEntity:
          Name:
            NameFull: Zhang, Xiao
      – PersonEntity:
          Name:
            NameFull: Wang, Rui
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20724292
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 7
          Titles:
            – TitleFull: Remote Sensing
              Type: main
ResultId 1