The swarm is now being asked to file its own route
the swarm is now being asked to file its own route: a destination earth service pairs rnn maxent models with climate data to map breeding grounds and forecasts migrations 5 to 20 days out, and a climate driven population model couples lstm temperatures with xgboost rainfall to catch the shift from solitary to gregarious.
the swarm now files its own trajectory.
Context
An EGU26 abstract describes the Desert Locust Monitoring Service on the Destination Earth platform with two layers. The first, Early-Stage Locust Appearance, uses a customized Maxent species distribution model to find areas with favorable breeding conditions, with a Safe Mode using 50 days of ERA5-Land climate data and Sentinel-3 NDVI for daily probability forecasts and an Experimental Mode that extends forecasts to two days using DestinE's Weather Extremes Digital Twin. The second layer, Locust Swarm Migration, uses a stochastic model that simulates movement on a 2D lattice and was trained, like Maxent, on a presence-only dataset from FAO's Locust Watch.
A Bulletin of Mathematical Biology paper, published August 21, 2026, couples a mechanistic stage- and phase-structured desert locust model with long short-term memory networks that predict temperature and gradient-boosting regression that predicts rainfall, and evaluates control interventions.
The note joins two separate things. The Destination Earth service is not described as using an RNN, and its breeding layer is Maxent with a stochastic lattice model for migration. The LSTM and gradient boosting belong to a different mathematical biology paper that couples forecasts to a population model.
The '5 to 20 days out' migration forecast was not found in the pages read. The abstract describes daily probability forecasts and a two day extension in the experimental mode, so the lead time is unsupported here, not refuted. 'XGBoost' is the note's word. The paper's abstract says gradient-boosting regression and the pages read do not name XGBoost.
The paper uses the solitarious and gregarious phase terms, and the note's 'shift from solitary to gregarious' matches that idea. Whether the model 'catches' the shift as a forecast is the author's description. The abstract reports that machine learning forcing reproduces observed climate variability better than harmonic forcing, not a validated swarm warning.
'The swarm now files its own trajectory' is the author's line.
Related work
- The Desert Locust Monitoring Service: a new Destination Earth service for Environmental Pest prediction (EGU26-22287) ↗Source for the Maxent layer, the Safe and Experimental modes and the stochastic migration layer.
- Desert Locust Monitoring Service (DestinE Platform) ↗DestinE's page for the service, operated by SISTEMA GmbH.
- Climate-Informed Predictive Optimal Control of Desert Locust Dynamics Under Machine-Learning Climate Forcing (Bulletin of Mathematical Biology, August 21, 2026) ↗Source for the LSTM temperature and gradient-boosting rainfall coupled to a locust population model.
Watch next
- Look in the service documentation for its migration forecast horizon. Check whether the Springer paper names XGBoost in its methods.
Sources
- DestinE Platform: Desert Locust Monitoring Serviceplatform.destine.eu
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 3 October 2026 at 18:07 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →