mlsanityData to 7 Oct 2026

Species Distribution Modeling for Machine Learning Practitioners: A Review

arXiv 2107.10400 ↗First posted 3 Jul 2021cs.LG stat.APcited by 21

Not on the map. Why?

Abstract (arXiv)

Conservation science depends on an accurate understanding of what's happening in a given ecosystem. How many species live there? What is the makeup of the population? How is that changing over time? Species Distribution Modeling (SDM) seeks to predict the spatial (and sometimes temporal) patterns of species occurrence, i.e. where a species is likely to be found. The last few years have seen a surge of interest in applying powerful machine learning tools to challenging problems in ecology. Despite its considerable importance, SDM has received relatively little attention from the computer science community. Our goal in this work is to provide computer scientists with the necessary background to read the SDM literature and develop ecologically useful ML-based SDM algorithms. In particular, we introduce key SDM concepts and terminology, review standard models, discuss data availability, and highlight technical challenges and pitfalls.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 20 of its 216 references that are in the map. First posted on arXiv 3 Jul 2021.

Builds on

20 of 216 references.

References · 20

  1. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  2. 2018Recognition in Terra Incognitacited by 655
  3. 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 167
  4. 2016Continuous Deep Q-Learning with Model-based Accelerationcited by 149
  5. 2019Presence-Only Geographical Priors for Fine-Grained Image Classificationcited by 109
  6. 2017The Devil is in the Tails: Fine-grained Classification in the Wildcited by 89
  7. 2020The iWildCam 2020 Competition Datasetcited by 86
  8. 2021The iWildCam 2021 Competition Datasetcited by 77
  9. 2019The Herbarium Challenge 2019 Datasetcited by 59
  10. 2016Deep Multi-Species Embeddingcited by 20
  11. 2017Wildbook: Crowdsourcing, computer vision, and data science for conservationcited by 20
  12. 2019iCassava 2019 Fine-Grained Visual Categorization Challengecited by 17
8 more
  1. 2019The iWildCam 2018 Challenge Datasetcited by 14
  2. 2020The Plant Pathology 2020 challenge dataset to classify foliar disease of applescited by 14
  3. 2018Performance evaluation and hyperparameter tuning of statistical and machine-learning models using spatial datacited by 11
  4. 2020The GeoLifeCLEF 2020 Datasetcited by 8
  5. 2019The iWildCam 2019 Challenge Datasetcited by 6
  6. 2017Multi-Entity Dependence Learning with Rich Context via Conditional Variational Auto-encodercited by 5
  7. 2019Evaluation of Deep Species Distribution Models using Environment and Co-occurrencescited by 2
  8. 2018Preferential sampling for presence/absence data and for fusion of presence/absence data with presence-only datacited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 6; 2024: 6; 2025: 4; 2026: 1.

21 papers.

Sort:

  1. 2021Seeing biodiversity: perspectives in machine learning for wildlife conservationcited by 129
  2. 2023Spatial Implicit Neural Representations for Global-Scale Species Mappingcited by 57
  3. 2023Active Learning-Based Species Range Estimationcited by 13
  4. 2024Combining Observational Data and Language for Species Range Estimationcited by 12
  5. 2022Machine Learning and Deep Learning -- A review for Ecologistscited by 11
  6. 2023Bird Distribution Modelling using Remote Sensing and Citizen Science datacited by 8
  7. 2022TIML: Task-Informed Meta-Learning for Agriculturecited by 7
  8. 2023LD-SDM: Language-Driven Hierarchical Species Distribution Modelingcited by 4
  9. 2024Generating Binary Species Range Mapscited by 4
  10. 2023SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Datacited by 3
  11. 2024Multi-Scale and Multimodal Species Distribution Modelingcited by 3
  12. 2025Feedforward Few-shot Species Range Estimationcited by 3
9 more
  1. 2026Localized, High-resolution Geographic Representations with Slepian Functionscited by 3
  2. 2023Conservation Tools: The Next Generation of Engineering--Biology Collaborationscited by 2
  3. 2025Foundation for unbiased cross-validation of spatio-temporal models for species distribution modelingcited by 2
  4. 2021On pseudo-absence generation and machine learning for locust breeding ground prediction in Africacited by 1
  5. 2024Predicting Species Occurrence Patterns from Partial Observationscited by 1
  6. 2024Hybrid Spatial Representations for Species Distribution Modelingcited by 1
  7. 2024Spatial Clustering of Citizen Science Data Improves Downstream Species Distribution Modelscited by 0
  8. 2025Heterogeneous graph neural networks for species distribution modelingcited by 0
  9. 2025Investigating Different Geo Priors for Image Classificationcited by 0