Conference paper · 2026 · Open access

Analysis and Prediction of Flood and Impact Estimation by Integrating CNN and LSTM Framework

Ashwini Kumar, Manish Mehta, Vishu Tyagi, Priyansh Kumar, Vikas Kumar, Ankur Chaudhary

International Conference on Green Technologies and Sustainable Solutions (GTSS), 299–304 · Published 1 February 2026 · DOI 10.1109/gtss68743.2026.11679762

Open full textCite this paper

In brief

“Analysis and Prediction of Flood and Impact Estimation by Integrating CNN and LSTM Framework” is a 2026 conference paper by Ashwini Kumar and 5 co-authors, published in International Conference on Green Technologies and Sustainable Solutions (GTSS). OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at International Conference on Green Technologies and Sustainable Solutions (GTSS).

Citations
0
References
23
Authors
6

Abstract

Flooding is one of the most destructive types of natural disasters; however, it is made worse by global warming and uncontrolled urban growth. Most of these traditional predictive techniques rely on old, very basic predictive models based solely on historical trends. Therefore, these predictive models cannot accommodate changes in either the climate or land usage, resulting in long delay times before action can be taken. In order to solve this problem, this study proposes an integrated system combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network, whose purpose is to forecast flooding and determine water overflow levels, particularly for dam-break scenarios. The proposed CNN-LSTM system was tested using a large synthetic dataset with the primary characteristics of dams including dam height, water elevation and storage volume. Spatial features were identified in each image layer of the CNN, while temporal relationships were determined by the LSTM layers. Results indicated that the integrated CNN-LSTM model provided superior predictive capability when compared to other predictive techniques used in this study such as Random Forest and the stand-alone CNN. Specifically, results from the proposed CNN-LSTM model demonstrated greater than 98% predictive accuracy and a low RMSE of 0.08. Furthermore, its high reliability and adaptability make the proposed CNN-LSTM model highly suitable for disaster management, providing communities with sufficient time to plan and execute preventative measures against future flooding events, improve their climate resiliency, and promote sustainable development by providing them with accurate and relevant flood forecasts.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Kumar, A., Mehta, M., Tyagi, V., Kumar, P., Kumar, V., & Chaudhary, A. (2026). Analysis and Prediction of Flood and Impact Estimation by Integrating CNN and LSTM Framework. International Conference on Green Technologies and Sustainable Solutions (GTSS), 299–304. https://doi.org/10.1109/gtss68743.2026.11679762

MLA 9

Kumar, Ashwini, et al. “Analysis and Prediction of Flood and Impact Estimation by Integrating CNN and LSTM Framework.” International Conference on Green Technologies and Sustainable Solutions (GTSS), 2026, pp. 299–304. https://doi.org/10.1109/gtss68743.2026.11679762.

Chicago

Kumar, Ashwini, Manish Mehta, Vishu Tyagi, Priyansh Kumar, Vikas Kumar, and Ankur Chaudhary. 2026. “Analysis and Prediction of Flood and Impact Estimation by Integrating CNN and LSTM Framework.” International Conference on Green Technologies and Sustainable Solutions (GTSS): 299–304. https://doi.org/10.1109/gtss68743.2026.11679762.

Harvard

Kumar, A. et al. (2026) ‘Analysis and Prediction of Flood and Impact Estimation by Integrating CNN and LSTM Framework’, International Conference on Green Technologies and Sustainable Solutions (GTSS), pp. 299–304. doi:10.1109/gtss68743.2026.11679762.

IEEE

A. Kumar, M. Mehta, V. Tyagi, P. Kumar, V. Kumar, and A. Chaudhary, “Analysis and Prediction of Flood and Impact Estimation by Integrating CNN and LSTM Framework,” International Conference on Green Technologies and Sustainable Solutions (GTSS), pp. 299–304, 2026, doi: 10.1109/gtss68743.2026.11679762.

BibTeX

@inproceedings{kumar2026analysis,
  title     = {{Analysis and Prediction of Flood and Impact Estimation by Integrating CNN and LSTM Framework}},
  author    = {Kumar, Ashwini and Mehta, Manish and Tyagi, Vishu and Kumar, Priyansh and Kumar, Vikas and Chaudhary, Ankur},
  booktitle = {International Conference on Green Technologies and Sustainable Solutions (GTSS)},
  year      = {2026},
  pages     = {299--304},
  doi       = {10.1109/gtss68743.2026.11679762},
  url       = {https://doi.org/10.1109/gtss68743.2026.11679762}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI

  • flood forecasting
  • CNN-LSTM hybrid model
  • convolutional neural networks
  • long short-term memory networks
  • disaster management
  • climate resilience
  • urban flooding

Work with this paper

Most-cited papers in Environmental Science

All highly cited Environmental Science papers

Questions about this paper

How do I cite this paper in APA style?

Kumar, A., Mehta, M., Tyagi, V., Kumar, P., Kumar, V., & Chaudhary, A. (2026). Analysis and Prediction of Flood and Impact Estimation by Integrating CNN and LSTM Framework. International Conference on Green Technologies and Sustainable Solutions (GTSS), 299–304. https://doi.org/10.1109/gtss68743.2026.11679762

How many times has this paper been cited?

0 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at International Conference on Green Technologies and Sustainable Solutions (GTSS): sign in and open the full text from this page.

Who wrote this paper?

Ashwini Kumar, Manish Mehta, Vishu Tyagi, Priyansh Kumar, Vikas Kumar, Ankur Chaudhary.

What is the DOI of this paper?

10.1109/gtss68743.2026.11679762, permanently at https://doi.org/10.1109/gtss68743.2026.11679762. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.