Spatioformer: A Geo-Encoded Transformer for Large-Scale Plant Species Richness Prediction

2024-10-25

IEEE Transactions on Geoscience and Remote Sensing

AI Summary

Remote sensing spectral signals exhibit spatial non-stationarity—i.e., location-dependent relationships with plant species richness—posing a fundamental challenge for large-scale biodiversity mapping. Method: We propose Spatioformer, a geographically aware Transformer model. It introduces a novel geographic position encoder that explicitly models β-diversity-driven spatial heterogeneity in the spectral–richness relationship, thereby relaxing the conventional assumption of spatial stationarity. Leveraging time-series Landsat imagery and ground-based HAVPlot data (68,170 plots), Spatioformer generates annual 1-km-resolution species richness maps across Australia (2015–2023). Results: Experiments demonstrate statistically significant improvements over state-of-the-art methods in prediction accuracy. Moreover, Spatioformer quantifies spatially explicit prediction uncertainty, enabling optimized design of targeted field surveys and enhancing ecological monitoring efficiency.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Earth observation (EO) data have shown promise in predicting species richness of vascular plants ( $alpha $ -diversity), but extending this approach to large spatial scales is challenging because geographically distant regions may exhibit different compositions of plant species ( $eta $ -diversity), resulting in a location-dependent relationship between richness and spectral measurements. In order to handle such geolocation dependence, we propose Spatioformer, where a novel geolocation encoder is coupled with the transformer model to encode geolocation context into remote sensing imagery. The Spatioformer model compares favorably to state-of-the-art models in richness predictions on a large-scale ground-truth richness dataset harmonized Australian vegetation plot (HAVPlot) that consists of 68 170 in situ richness samples covering diverse landscapes across Australia. The results demonstrate that geolocational information is advantageous in predicting species richness from satellite observations over large spatial scales. With Spatioformer, plant species richness maps over Australia are compiled from the Landsat archive for the years from 2015 to 2023. The richness maps produced in this study reveal the spatiotemporal dynamics of plant species richness in Australia, providing supporting evidence to inform effective planning and policy development for plant diversity conservation. Regions of high richness prediction uncertainties are identified, highlighting the need for future in situ surveys to be conducted in these areas to enhance the prediction accuracy.

Problem

• Predict plant species richness at large spatial scales
• Address geolocation dependency in species richness prediction
• Enhance accuracy of species richness maps using geolocation

Innovation

• Geolocation encoder integrated with transformer model
• Predicts plant species richness using satellite data
• Generates spatiotemporal richness maps for conservation planning