# Inferring the past: a combined CNN-LSTM deep learning framework to fuse satellites for historical inundation mapping

arXiv: https://arxiv.org/abs/2305.00640 · HTML: https://mlsanity.com/paper/2305.00640/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 56 references that are in the map.
- First posted on arXiv 1 May 2023.

## Builds on (most cited first, 7 of 7)

- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Wider or Deeper: Revisiting the ResNet Model for Visual Recognition](https://mlsanity.com/paper/1611.10080/) (2016)
- [A trans-disciplinary review of deep learning research for water resources scientists](https://mlsanity.com/paper/1712.02162/) (2017)
- [Optimizing Deeper Transformers on Small Datasets](https://mlsanity.com/paper/2012.15355/) (2020)
- [DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn](https://mlsanity.com/paper/1809.07589/) (2018)
- [A Novel CNN-LSTM-based Approach to Predict Urban Expansion](https://mlsanity.com/paper/2103.01695/) (2021)
- [NeuralHydrology -- Interpreting LSTMs in Hydrology](https://mlsanity.com/paper/1903.07903/) (2019)

## Built on by (most cited first, 4 of 4)

- [Conformal Prediction for Generative Models via Adaptive Cluster-Based Density Estimation](https://mlsanity.com/paper/2601.22298/) (2026)
- [Assessing the value of Geo-Foundational Models for Flood Inundation Mapping: Benchmarking models for Sentinel-1, Sentinel-2, and Planetscope for end-users](https://mlsanity.com/paper/2511.01990/) (2025)
- [Image-to-Text for Medical Reports Using Adaptive Co-Attention and Triple-LSTM Module](https://mlsanity.com/paper/2503.18297/) (2025)
- [Urban Flood Observations: A hand-labeled training and validation dataset of post-flood inundation](https://mlsanity.com/paper/2604.23066/) (2026)

## Abstract (arXiv)

Mapping floods using satellite data is crucial for managing and mitigating flood risks. Satellite imagery enables rapid and accurate analysis of large areas, providing critical information for emergency response and disaster management. Historical flood data derived from satellite imagery can inform long-term planning, risk management strategies, and insurance-related decisions. The Sentinel-1 satellite is effective for flood detection, but for longer time series, other satellites such as MODIS can be used in combination with deep learning models to accurately identify and map past flood events. We here develop a combined CNN--LSTM deep learning framework to fuse Sentinel-1 derived fractional flooded area with MODIS data in order to infer historical floods over Bangladesh. The results show how our framework outperforms a CNN-only approach and takes advantage of not only space, but also time in order to predict the fractional inundated area. The model is applied to historical MODIS data to infer the past 20 years of inundation extents over Bangladesh and compared to a thresholding algorithm and a physical model. Our fusion model outperforms both models in consistency and capacity to predict peak inundation extents.