aiqbench analysis
This research introduces RNN Maxent, a novel framework that integrates Gated Recurrent Units into the standard Maxent algorithm to capture nonlinear temporal dynamics in species distribution modeling. By replacing fixed feature transforms with learned neural nonlinearity, the method significantly improves forecasting accuracy for presence-only data, as demonstrated by superior performance metrics in Desert Locust habitat mapping. The approach maintains key statistical properties of Maxent while leveraging sequential environmental time series to better reflect evolving ecological conditions.
Neural-Network Maxent: a general extension with learned nonlinearity, applied to time-series for Desert Locust distribution modelling
arXiv:2609.03603v1 Announce Type: new Abstract: Species Distribution Modelling (SDM) is essential for understanding how environmental conditions shape biodiversity, particularly for destructive pests such as the Desert Locust (Schistocerca gregaria), whose breeding dynamics are tightly coupled to rapidly evolving environmental conditions. Maxent has become the dominant method for presence-only data, but its reliance on a linear combination of hand chosen feature transforms limits its ability to capture the nonlinear, temporal relationships common in ecological monitoring, where covariates such as precipitation, soil moisture, and vegetation indices evolve meaningfully over time. Standard implementations flatten time-series covariates into independent features, discarding sequential structure that carries critical signal. We introduce RNN Maxent, an extension of the Maxent framework that replaces the fixed feature dictionary with a neural network, specifically a Gated Recurrent Unit (GRU), trained end to end via backpropagation. The approach preserves Maxent's presence only statistical foundations, background normalization, and probability calibration, differing only in that the nonlinearity is learned from data rather than fixed in advance. We apply RNN Maxent to map suitable habitat for the Desert Locust using 50 day environmental time series derived from ERA5 Land, MODIS, and Sentinel 3, maintaining a 7 day gap between covariates and presence records to yield forecasting behavior. Compared against standard Maxent, RNN Maxent improves performance across metrics (ROC AUC 0.862 std 0.036 vs. 0.792; F1 0.671 std 0.056 vs. 0.590).
Abstract:Species Distribution Modelling (SDM) is essential for understanding how environmental conditions shape biodiversity, particularly for destructive pests such as the Desert Locust (Schistocerca gregaria), whose breeding dynamics are tightly coupled to rapidly evolving environmental conditions. Maxent has become the dominant method for presence-only data, but its reliance on a linear combination of hand chosen feature transforms limits its ability to capture the nonlinear, temporal relationships common in ecological monitoring, where covariates such as precipitation, soil moisture, and vegetation indices evolve meaningfully over time. Standard implementations flatten time-series covariates into independent features, discarding sequential structure that carries critical signal. We introduce RNN Maxent, an extension of the Maxent framework that replaces the fixed feature dictionary with a neural network, specifically a Gated Recurrent Unit (GRU), trained end to end via backpropagation. The approach preserves Maxent's presence only statistical foundations, background normalization, and probability calibration, differing only in that the nonlinearity is learned from data rather than fixed in advance. We apply RNN Maxent to map suitable habitat for the Desert Locust using 50 day environmental time series derived from ERA5 Land, MODIS, and Sentinel 3, maintaining a 7 day gap between covariates and presence records to yield forecasting behavior. Compared against standard Maxent, RNN Maxent improves performance across metrics (ROC AUC 0.862 std 0.036 vs. 0.792; F1 0.671 std 0.056 vs. 0.590).
Machine Learning (cs.LG); Image and Video Processing (eess.IV); Data Analysis, Statistics and Probability (physics.data-an); Populations and Evolution (q-bio.PE)
arXiv:2609.03603 [cs.LG]
(or arXiv:2609.03603v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.03603 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 254 words
Related coverage
Generalization and infinite width
LessWrong · Aug 1, 2026
Finite Element-Based Material Learning via Automatic Differentiation: Learning constitutive neural network models from full-field deformation data
arXiv · Jun 6, 2026
Physics-Informed Stochastic Configuration Machine: A Backpropagation-Free Neural Network with Fast Training for Nonlinear Differential Equations
arXiv · Aug 28, 2026
Radiomic Feature Selection Using Gradient Loss of Deep Neural Network for Lung Cancer Stage Detection
arXiv · Jun 5, 2026