# On the selection and effectiveness of pseudo-absences for species distribution modeling with deep learning

arXiv: https://arxiv.org/abs/2401.02989 · HTML: https://mlsanity.com/paper/2401.02989/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 75 references that are in the map.
- First posted on arXiv 3 Jan 2024.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [Learning from positive and unlabeled data: a survey](https://mlsanity.com/paper/1811.04820/) (2018)
- [Seeing biodiversity: perspectives in machine learning for wildlife conservation](https://mlsanity.com/paper/2110.12951/) (2021)
- [Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets](https://mlsanity.com/paper/2007.09654/) (2020)
- [Presence-Only Geographical Priors for Fine-Grained Image Classification](https://mlsanity.com/paper/1906.05272/) (2019)
- [Multi-Label Learning from Single Positive Labels](https://mlsanity.com/paper/2106.09708/) (2021)
- [Spatial Implicit Neural Representations for Global-Scale Species Mapping](https://mlsanity.com/paper/2306.02564/) (2023)
- [Acknowledging the Unknown for Multi-label Learning with Single Positive Labels](https://mlsanity.com/paper/2203.16219/) (2022)
- [Deep Multi-Species Embedding](https://mlsanity.com/paper/1609.09353/) (2016)

## Built on by (most cited first, 10 of 10)

- [GeoPlant: Spatial Plant Species Prediction Dataset](https://mlsanity.com/paper/2408.13928/) (2024)
- [Imbalance-aware Presence-only Loss Function for Species Distribution Modeling](https://mlsanity.com/paper/2403.07472/) (2024)
- [Generating Binary Species Range Maps](https://mlsanity.com/paper/2408.15956/) (2024)
- [Multi-Scale and Multimodal Species Distribution Modeling](https://mlsanity.com/paper/2411.04016/) (2024)
- [Feedforward Few-shot Species Range Estimation](https://mlsanity.com/paper/2502.14977/) (2025)
- [MaskSDM with Shapley values to improve flexibility, robustness, and explainability in species distribution modeling](https://mlsanity.com/paper/2503.13057/) (2025)
- [CISO: Species Distribution Modeling Conditioned on Incomplete Species Observations](https://mlsanity.com/paper/2508.06704/) (2025)
- [Applying the maximum entropy principle to neural networks enhances multi-species distribution models](https://mlsanity.com/paper/2412.19217/) (2024)
- [Heterogeneous graph neural networks for species distribution modeling](https://mlsanity.com/paper/2503.11900/) (2025)
- [SAGE: A sampling-aware global evaluation benchmark for species distribution modeling](https://mlsanity.com/paper/2609.31082/) (2026)

## Abstract (arXiv)

Species distribution modeling is a highly versatile tool for understanding the intricate relationship between environmental conditions and species occurrences. However, the available data often lacks information on confirmed species absence and is limited to opportunistically sampled, presence-only observations. To overcome this limitation, a common approach is to employ pseudo-absences, which are specific geographic locations designated as negative samples. While pseudo-absences are well-established for single-species distribution models, their application in the context of multi-species neural networks remains underexplored. Notably, the significant class imbalance between species presences and pseudo-absences is often left unaddressed. Moreover, the existence of different types of pseudo-absences (e.g., random and target-group background points) adds complexity to the selection process. Determining the optimal combination of pseudo-absences types is difficult and depends on the characteristics of the data, particularly considering that certain types of pseudo-absences can be used to mitigate geographic biases. In this paper, we demonstrate that these challenges can be effectively tackled by integrating pseudo-absences in the training of multi-species neural networks through modifications to the loss function. This adjustment involves assigning different weights to the distinct terms of the loss function, thereby addressing both the class imbalance and the choice of pseudo-absence types. Additionally, we propose a strategy to set these loss weights using spatial block cross-validation with presence-only data. We evaluate our approach using a benchmark dataset containing independent presence-absence data from six different regions and report improved results when compared to competing approaches.