Popular GitHub Repositories for Flood Hazards

Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).

Enhances construction site safety using YOLO for object detection, identifying hazards like workers without helmets or safety vests, and proximity to machinery or vehicles. HDBSCAN clusters safety cone coordinates to create monitored zones. Post-processing algorithms improve detection accuracy.

Flood detection from images using deep learning. Deep learning library KERAS was employed and MobileNet architecture was fine-tuned for image classification task.

Using Machine Learning algorithms to predict the chances of Flood in the state of Kerala.

Flood warning using RNN and clustering on live water level data

Variational Bayes for High-Dimensional Survival Analysis https://arxiv.org/abs/2112.10270

Flood Fill Network for 3d Electron Microscopy volume neuron segmentation. Adapt from google FFN-master add notes and custom variation and parallelization (for windows and our retina & LGN data)

Implementation of FGSM (Fast Gradient Sign Method) attack on fine-tuned MobileNet architecture trained for flood detection in images.

This project leverages TensorFlow and Keras to build and train a neural network model for predicting flood probability based on various environmental and socio-economic factors.

Rapid Roll is a classic mobile game originally found on Nokia 1280 devices. In the game, the player controls a ball that continuously falls and must land on moving platforms while avoiding spike traps. The objective is to survive as long as possible by staying on platforms and avoiding hazards.

IceWatch: Glacial Lake Outburst Flood (GLOF) Prediction System Using Deep Learning. Now live at (try using it in light mode)

IceWatch: Glacial Lake Outburst Flood (GLOF) Prediction System Using Deep Learning. Now live at (try using it in light mode)

CSOD is an advanced computer vision project that uses the YOLOv5 model, fine-tuned on thousands of images, to detect safety hazards on construction sites in real-time. This technology helps identify potential dangers like missing helmets or safety vests, ensuring a safer work environment for everyone on site.

A Natural Language Processing (NLP) project for SemEval 2025 Task 9, using DistilBERT with a custom attention mechanism that integrates textual and temporal features to detect food hazards in text.

Flood-Image-Detection is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-512 for binary image classification. It is trained to detect whether an image contains a flooded scene or non-flooded environment. The model uses the SiglipForImageClassification architecture.

EMSUGI is a future prediction & analysis project on various factor like flood, earth quake, disease occurred on your neighborhood location.

An AI Agent powered web application that helps parents and guardians detect child safety hazards in home environments, plan safer outdoor activities, and discover child-proofing products.

Predicte the urban flooding based on the LightGBM model

Solution for SemEval-2025 Task 9: The Food Hazard Detection Challenge. Utilized machine learning, fine-tuned LLMs (GPT-2, LLaMA, Flan-T5-XL), and ensemble learning to classify food hazards and detect specific products and hazards from unstructured text.

Repo containing model training on high resolution flood response drone RGB drone imagery with pytorch and semantic segmentation models.