Open-source disaster risk intelligence platform for US municipalities — powered by FEMA, USGS & NOAA public data

Off-grid IR mesh network that retrofits solar street lamps for disaster communication — gradient routing, no power grid, no mobile network needed.

A deep reinforcement learning system for optimizing bridge maintenance decisions across municipal infrastructure fleets, implementing cross-subsidy budget sharing and cooperative multi-agent learning.

Quantile Regression DQN implementation for bridge fleet maintenance optimization using Markov Decision Process. Migrated from C51 distributional RL (v0.8) with 200 quantiles and Huber loss. Features: Dueling architecture, Noisy Networks, PER, N-step learning. All 6 maintenance actions show positive returns with 68-78% VaR improvement.

There are already applications for managing and distributing waste in Indonesia. With those apps as a reference, we tried to design a similar application by emphasizing the unique aspects of sorting and channeling types of residential waste. We want to make an application that can detect six types of residential waste by scanning the camera on a…

Deep Q-Network implementation for optimal bridge maintenance planning using Markov Decision Process formulation with vectorized parallel training. Based on Phase 3 (Vectorized DQN) from dql-maintenance-faster project.

Deep Q-Network (DQN) implementation for optimal maintenance planning of 100-bridge fleet infrastructure using advanced reinforcement learning techniques and vectorized parallel training.

W.O.M.B.A.T. Terminal Offline Edition

A comprehensive reinforcement learning system for pump equipment condition-based maintenance using DQN (Deep Q-Network) with quantile regression and aging factor integration.

A Reinforcement Learning MVP (Minimum Viable Product) for Condition-Based Maintenance (CBM) using industrial equipment temperature sensor data. This project implements a sophisticated QR-DQN (Quantile Regression Deep Q-Network) agent to learn optimal maintenance policies balancing risk mitigation and cost minimization.

This tool applies self-improving (Agentic) clustering to bridge maintenance data in Open data at some Prefecture, Japan, to automatically identify bridge groups with high maintenance priority.

This project applies self-improving (Agentic) clustering with Bayesian Optimization to bridge maintenance data in some Prefecture, Japan, to automatically identify bridge groups with high maintenance priority.

Multi-Equipment CBM system using QR-DQN with advanced probability distribution analysis. Coordinated maintenance decision-making for 4 industrial equipment units with realistic anomaly rates (1.9-2.2%), comprehensive risk analysis (VaR/CVaR), and 51-quantile distribution visualization.

Aging-Aware Condition-Based Maintenance System using Deep Q-Learning. This project implements a Condition-Based Maintenance (CBM) system that considers equipment aging (deterioration) using Deep Q-Learning (DQN).

C51 Distributional DQN (v0.8) for bridge fleet maintenance optimization. Implements categorical return distributions (Bellemare et al., PMLR 2017) with 300x speedup via vectorized projection. Combines Noisy Networks, Dueling DQN, Double DQN, PER, and n-step learning. Validated on 200-bridge fleet: +3,173 reward in 83 min (25k episodes).

Bridge criticality clustering system with LLM interpretation using UMAP + HDBSCAN. Analyzes urban infrastructure importance from 100% open data (OpenStreetMap, government stats).

Markov Decision Process DQN with Noisy Networks for Exploration (ICLR 2018) - 21.1% performance improvement over ε-greedy.

Community Resilience Estimates Tool 2019

Multi-Equipment CBM (Condition-Based Maintenance) optimization using Deep Q-Learning with cost leveling and scenario comparison. Advanced RL system with QR-DQN, N-step learning, and parallel environments for HVAC equipment predictive maintenance.

Provide local disaster risk intelligence by combining federal hazard data into accessible risk scores via API and interactive maps.