An AI-driven fire risk forecasting framework for urban villages using IGWO-optimized LSTM with incremental learning

Jiangxue Tian, Handong Li, Shuran Lv · 2026

Read An AI-driven fire risk forecasting framework for urban villages using IGWO-optimized LSTM with incremental learning by Jiangxue Tian, Handong Li, Shuran Lv (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0350182.txt.

Description

Jiangxue Tian, Handong Li, and Shuran Lv built a fire risk forecasting system for Beijing's urban villages in 2026. These dense settlements mix homes and workshops with weak infrastructure, making fire both likely and deadly.

Their model pairs a long memory neural network with an improved swarm search that tunes it, plus step by step updating so it learns from fresh incidents without full retraining. Fed with real fire records from fifty-five villages, it cut forecast error sharply against a plain network. City teams could use such forecasts to aim inspections and crews at the blocks most likely to burn next.

Catalog record

CREATORJiangxue Tian, Handong Li, Shuran Lv
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE55150
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0350182

Browse the full library · About the Tower of Babel