View in EDS HTML Full Text PDF Full Text

Meta-Learning in Land Use and Land Cover Classification: Review and Perspective.

Saved in:
Bibliographic Details
Title: Meta-Learning in Land Use and Land Cover Classification: Review and Perspective.
Authors: He, Wei1,2 (AUTHOR), Li, Lianfa1,2 (AUTHOR) lilf@lreis.ac.cn, Wu, Haoxiong1,2,3 (AUTHOR), Gao, Xilin1,2 (AUTHOR), Yang, Yichen1,2 (AUTHOR), Zhang, Zixuan3 (AUTHOR), Yang, Xiaomei1,2 (AUTHOR), Ge, Yong1,2 (AUTHOR)
Source: Remote Sensing. Jun2026, Vol. 18 Issue 12, p1879. 34p.
Subjects: Land use mapping, Remote sensing, Deep learning, Machine learning, Multisensor data fusion
Abstract: Highlights: What are the main findings? Optimization-based and metric-based meta-learning dominate LULC classification research, with MAML and its variants being the most widely adopted, while memory-augmented methods remain underexplored due to computational overhead on high-dimensional remote sensing data. Meta-learning consistently outperforms conventional pre-training followed by fine-tuning under significant domain shifts across multiple data modalities, by acquiring cross-task structural knowledge rather than reusing instance-level features. What are the implications of the main findings? Temporal dynamics modeling and multimodal data integration remain in early stages, calling for unified meta-learning frameworks that jointly address cross-regional, cross-temporal, and cross-modal generalization challenges arising from spatial heterogeneity. The integration of meta-learning with remote sensing foundation models represents a promising pathway toward operationally deployable LULC systems, combining large-scale representation learning with rapid few-shot adaptation mechanisms. Deep learning has exhibited potential in land use and land cover (LULC) classification applications. However, the effectiveness of deep learning remains constrained by the availability and quality of annotated training data. The persistent scarcity of labeled samples and spatial heterogeneity of remote sensing imagery hinder the robustness and generalization of trained models. Meta-learning, commonly referred to as "learning to learn", is a paradigm that trains models over a distribution of tasks to acquire transferable knowledge, enabling rapid adaptation to new tasks with only a few labeled samples. This cross-task learning capability makes meta-learning a promising solution to data scarcity and spatial heterogeneity in the remote sensing context. This paper provides a systematic review of meta-learning applications in LULC classification, identifying a total of 70 relevant studies between 2018 and 2025. Three mainstream meta-learning paradigms (memory-augmented, optimization-based, and metric-based) are reviewed, and the applications are analyzed across four core challenges in LULC remote sensing: label scarcity, cross-region and cross-domain distribution shifts, temporal dynamics modeling, and multimodal data integration. The review reveals that optimization-based and metric-based methods dominate current research, with MAML and its variants being the most widely adopted due to the model-agnostic property, while memory-augmented methods remain underexplored. A consistent finding is that meta-learning outperforms conventional pre-training followed by fine-tuning under significant domain shifts across multiple data modalities. Current limitations, including computational overhead, episodic training constraints, and the lack of standardized evaluation protocols, are discussed. Future directions in cross-domain generalization, integration with foundation models, novel architectures, and standardized benchmarks are identified. [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: 194915012
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Meta-Learning in Land Use and Land Cover Classification: Review and Perspective.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22He%2C+Wei%22">He, Wei</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Lianfa%22">Li, Lianfa</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> lilf@lreis.ac.cn</i><br /><searchLink fieldCode="AR" term="%22Wu%2C+Haoxiong%22">Wu, Haoxiong</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gao%2C+Xilin%22">Gao, Xilin</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yang%2C+Yichen%22">Yang, Yichen</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Zixuan%22">Zhang, Zixuan</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yang%2C+Xiaomei%22">Yang, Xiaomei</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ge%2C+Yong%22">Ge, Yong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Jun2026, Vol. 18 Issue 12, p1879. 34p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Land+use+mapping%22">Land use mapping</searchLink><br /><searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Multisensor+data+fusion%22">Multisensor data fusion</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Highlights: What are the main findings? Optimization-based and metric-based meta-learning dominate LULC classification research, with MAML and its variants being the most widely adopted, while memory-augmented methods remain underexplored due to computational overhead on high-dimensional remote sensing data. Meta-learning consistently outperforms conventional pre-training followed by fine-tuning under significant domain shifts across multiple data modalities, by acquiring cross-task structural knowledge rather than reusing instance-level features. What are the implications of the main findings? Temporal dynamics modeling and multimodal data integration remain in early stages, calling for unified meta-learning frameworks that jointly address cross-regional, cross-temporal, and cross-modal generalization challenges arising from spatial heterogeneity. The integration of meta-learning with remote sensing foundation models represents a promising pathway toward operationally deployable LULC systems, combining large-scale representation learning with rapid few-shot adaptation mechanisms. Deep learning has exhibited potential in land use and land cover (LULC) classification applications. However, the effectiveness of deep learning remains constrained by the availability and quality of annotated training data. The persistent scarcity of labeled samples and spatial heterogeneity of remote sensing imagery hinder the robustness and generalization of trained models. Meta-learning, commonly referred to as "learning to learn", is a paradigm that trains models over a distribution of tasks to acquire transferable knowledge, enabling rapid adaptation to new tasks with only a few labeled samples. This cross-task learning capability makes meta-learning a promising solution to data scarcity and spatial heterogeneity in the remote sensing context. This paper provides a systematic review of meta-learning applications in LULC classification, identifying a total of 70 relevant studies between 2018 and 2025. Three mainstream meta-learning paradigms (memory-augmented, optimization-based, and metric-based) are reviewed, and the applications are analyzed across four core challenges in LULC remote sensing: label scarcity, cross-region and cross-domain distribution shifts, temporal dynamics modeling, and multimodal data integration. The review reveals that optimization-based and metric-based methods dominate current research, with MAML and its variants being the most widely adopted due to the model-agnostic property, while memory-augmented methods remain underexplored. A consistent finding is that meta-learning outperforms conventional pre-training followed by fine-tuning under significant domain shifts across multiple data modalities. Current limitations, including computational overhead, episodic training constraints, and the lack of standardized evaluation protocols, are discussed. Future directions in cross-domain generalization, integration with foundation models, novel architectures, and standardized benchmarks are identified. [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=194915012
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs18121879
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 34
        StartPage: 1879
    Subjects:
      – SubjectFull: Land use mapping
        Type: general
      – SubjectFull: Remote sensing
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Multisensor data fusion
        Type: general
    Titles:
      – TitleFull: Meta-Learning in Land Use and Land Cover Classification: Review and Perspective.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: He, Wei
      – PersonEntity:
          Name:
            NameFull: Li, Lianfa
      – PersonEntity:
          Name:
            NameFull: Wu, Haoxiong
      – PersonEntity:
          Name:
            NameFull: Gao, Xilin
      – PersonEntity:
          Name:
            NameFull: Yang, Yichen
      – PersonEntity:
          Name:
            NameFull: Zhang, Zixuan
      – PersonEntity:
          Name:
            NameFull: Yang, Xiaomei
      – PersonEntity:
          Name:
            NameFull: Ge, Yong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20724292
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 12
          Titles:
            – TitleFull: Remote Sensing
              Type: main
ResultId 1