Biodiversity assessments are critically affected by the spatial scale at which species richness is measured. How species richness accumulates with sampling area depends on natural and anthropogenic processes whose effects can change depending on the spatial scale considered. These accumulation dynamics, described by the species-area relationship (SAR), are challenging to assess because most biodiversity surveys are restricted to sampling areas much smaller than the scales at which these processes operate. Here, we combine sampling theory and deep learning to predict local species richness within arbitrarily large sampling areas, enabling for the first time to estimate spatial differences in SARs. We demonstrate our approach by predicting vascular plant species richness across Europe and evaluate predictions against an independent dataset of plant community inventories. The resulting model, named deep SAR, delivers multi-scale species richness maps, improving coarse grain richness estimates by 32% compared to conventional methods, while delivering finer grain estimates. Additional to its predictive capabilities, we show how our deep SAR model can provide fundamental insights on the multi-scale effects of key biodiversity processes. The capacity of our approach to deliver comprehensive species richness estimates across the full spectrum of ecologically relevant scales is essential for robust biodiversity assessments and forecasts under global change.

Earth observation 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 ($\beta$-diversity), resulting in a location-dependent relationship between richness and spectral measurements. In order to handle such geolocation dependency, 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 favourably to state-of-the-art models in richness predictions on a large-scale ground-truth richness dataset (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 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.

One key task in environmental science is to map environmental variables continuously in space or even in space and time. Machine learning algorithms are frequently used to learn from local field observations to make spatial predictions by estimating the value of the variable of interest in places where it has not been measured. However, the application of machine learning strategies for spatial mapping involves additional challenges compared to "non-spatial" prediction tasks that often originate from spatial autocorrelation and from training data that are not independent and identically distributed. In the past few years, we developed a number of methods to support the application of machine learning for spatial data which involves the development of suitable cross-validation strategies for performance assessment and model selection, spatial feature selection, and methods to assess the area of applicability of the trained models. The intention of the CAST package is to support the application of machine learning strategies for predictive mapping by implementing such methods and making them available for easy integration into modelling workflows. Here we introduce the CAST package and its core functionalities. At the case study of mapping plant species richness, we will go through the different steps of the modelling workflow and show how CAST can be used to support more reliable spatial predictions.

The reliable mapping of species richness is a crucial step for the identification of areas of high conservation priority, alongside other value and threat considerations. This is commonly done by overlapping range maps of individual species, which requires dense availability of occurrence data or relies on assumptions about the presence of species in unsampled areas deemed suitable by environmental niche models. Here, we present a deep learning approach that directly estimates species richness, skipping the step of estimating individual species ranges. We train a neural network model based on species lists from inventory plots, which provide ground truth data for supervised machine learning. The model learns to predict species richness based on spatially associated variables, including climatic and geographic predictors, as well as counts of available species records from online databases. We assess the empirical utility of our approach by producing independently verifiable maps of alpha, beta, and gamma plant diversity at high spatial resolutions for Australia, a continent with highly heterogeneous diversity patterns. Our deep learning framework provides a powerful and flexible new approach for estimating biodiversity patterns, constituting a step forward toward automated biodiversity assessments.

Quantifying biodiversity is an important task related to ecological research. One way to measure biodiversity is through species richness, which measures the number of unique species found in an area. Recently, citizen science biodiversity datasets such as eBird allow the calculation of species richness over an unprecedented spatial and temporal extent. However, several confounding factors associated with the unstructured observation process, such as observer effort, affect the number of species reported by citizen scientists. In this work, we develop an algorithm for discovering hotspots and coldspots of species richness using eBird data while accounting for these confounding factors.