Artificial intelligence and geospatial technologies for biodiversity hotspot research: a Scopus-based bibliometric review and implications for Uzbekistan
Keywords:
artificial intelligence, machine learning, Random Forest, remote sensing, geographic information systems, biodiversity hotspot, species distribution modelling, UzbekistanAbstract
The convergence of artificial intelligence (AI), machine learning and geospatial technologies has transformed how ecologists detect, map and monitor biodiversity in threatened landscapes. This review synthesises 82 peer-reviewed articles retrieved from Scopus (2013-2025) applying AI, GIS and remote-sensing-based methods to biodiversity hotspot research. A PRISMA-adapted procedure reduced an initial 800 records to 82 relevant documents, 82 of which were fully analysed. Annual output expanded sharply after 2018, with most documents published in 2023-2025. Random Forest was the dominant algorithm (34 of 82 documents), followed by species-distribution-modelling frameworks (20), Sentinel-1/2 imagery (18) and deep learning (15). The literature clusters around machine-learning classification, deep-learning survey interpretation, UAV/hyperspectral/LiDAR platforms, satellite monitoring, eDNA and citizen-science integration, and invasive-species detection. The United States, India and Brazil were the most cited producing countries; Remote Sensing, Ecological Informatics and Ecological Indicators were the leading outlets. No study addressed Uzbekistan or Central Asia, revealing a clear geographical gap, although transferable evidence from arid, steppe and grassland ecosystems elsewhere is identified. AI-assisted geospatial monitoring is methodologically mature for operational use, but its transfer to data-scarce Central Asian contexts requires dedicated empirical validation, capacity building and open-data infrastructure.
References
Ahmadi K.; Mahmoodi S.; Pal S.C.; et al. (2023). Improving species distribution models for dominant trees in climate data-poor forests using high-resolution remote sensing. Ecological Modelling, 475.
Antonelli A.; Dhanjal-Adams K.L.; Silvestro D. (2023). Integrating machine learning, remote sensing and citizen science to create an early warning system for biodiversity. Plants People Planet, 5(3), 307-316.
Arasumani M.; Singh A.; Bunyan M.; Robin V.V. (2021). Testing the efficacy of hyperspectral (AVIRIS-NG), multispectral (Sentinel-2) and radar (Sentinel-1) remote sensing images to detect native and invasive non-native trees. Biological Invasions, 23(9), 2863-2879.
Bauknecht R.; Pellissier L.; Brosse S.; et al. (2025). Combining environmental DNA and remote sensing variables to model fish biodiversity in tropical river ecosystems. Ecological Informatics, 90.
Bizzozzero M.R.; Marfurt S.M.; Altermatt F.; et al. (2025). Integrating Environmental DNA Metabarcoding and Remote Sensing Reveals Known and Novel Fish Diversity Hotspots in a World Heritage Area. Diversity and Distributions, 31(11).
Cheng K.; Zhang C.; Fan Y.; Diao H.; Xia S. (2025). AI-based approaches for wetland mapping and classification: A review of current practices and future perspectives. Artificial Intelligence in Geosciences, 6(2).
Jiang X.; Zhang L.; Feng K.; et al. (2025). Mapping urban waterbird habitats using machine learning and citizen science: A multi-scale analysis in Brussels, Belgium. Journal of Environmental Management, 395.
Krämer A.; Meyer H.; Buchholz S. (2025). Habitat Suitability of the Sand Lizard (Lacerta agilis) at Its Distribution Limit — An Analysis Based on Citizen Science Data and Machine Learning. Journal of Biogeography, 52(5).
Li Y.; Devenish C.; Tosa M.I.; et al. (2024). Combining environmental DNA and remote sensing for efficient, fine-scale mapping of arthropod biodiversity. Philosophical Transactions of the Royal Society B: Biological Sciences, 379(1904).
Mashiane K.; Ramoelo A.; Adelabu S. (2024). Prediction of species richness and diversity in sub-alpine grasslands using satellite remote sensing and random forest machine-learning algorithm. Applied Vegetation Science, 27(2).
Muthoka J.M.; Salakpi E.E.; Ouko E.; et al. (2021). Mapping Opuntia stricta in the arid and semi-arid environment of Kenya using Sentinel-2 imagery and ensemble machine learning classifiers. Remote Sensing, 13(8).
Pettorelli N.; Williams J.; Schulte to Bühne H.; Crowson M. (2025). Deep learning and satellite remote sensing for biodiversity monitoring and conservation. Remote Sensing in Ecology and Conservation, 11(2), 123-132.
Reddy C.S.; Athira K.; Mudalkar S. (2025). Evolution of Global Biodiversity Monitoring: Innovations, Modern Approaches and Integration with Essential Variables. Journal of the Indian Society of Remote Sensing, 53(7), 2017-2030.
Satish K.V.; Dugesar V.; Pandey M.K.; et al. (2023). Seeing from space makes sense: Novel earth observation variables accurately map species distributions over Himalaya. Journal of Environmental Management, 325.
Tang Z.; Xuan C.; Zhang T.; et al. (2025). A Novel Remote Sensing Framework Integrating Geostatistical Methods and Machine Learning for Spatial Prediction of Diversity Indices in the Desert Steppe. Agriculture (Switzerland), 15(18).
Thuiller W.; Saillard A.; Abdulhak S.; et al. (2024). ORCHAMP: an observation network for monitoring biodiversity and ecosystem functioning across space and time in mountainous regions. Comptes Rendus - Biologies, 347, 223-247.
Timmermans J.; Daniel Kissling W. (2023). Advancing terrestrial biodiversity monitoring with satellite remote sensing in the context of the Kunming-Montreal global biodiversity framework. Ecological Indicators, 154.
Venter Z.S.; Roos R.E.; Nowell M.S.; et al. (2023). Comparing Global Sentinel-2 Land Cover Maps for Regional Species Distribution Modeling. Remote Sensing, 15(7).
Zhidebayeva A.; Syrlybekkyzy S.; Taizhanova L.; et al. (2025). Emerging frontiers in ecosystem and biodiversity monitoring using remote sensing and geographic information systems. Global Journal of Environmental Science and Management, 11(4), 1791-1818.
Zong S.; Brantschen J.; Zhang X.; et al. (2024). Combining environmental DNA with remote sensing variables to map fish species distributions along a large river. Remote Sensing in Ecology and Conservation, 10(2), 220-235.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
