We're Team Arson and we're using the power of predictive modeling to combat wildfires.

Overview

Logo We're Team Arson and we're using the power of predictive modeling to combat wildfires.

Arson Map

Inspiration

There’s been a lot of wildfires in California in recent years, and a lot of the most recent wildfires have been uncontained. The government does not have the capacity to deal with such a huge amount of wildfires so it has to pick and choose which fires to bring under control. This picking and choosing should be done based on wildfire and wind data in order to minimize the damage caused by wildfires We should also prioritize mitigating fires that can spread across many counties/ have a large chance of spreading further

What it does

Our project consists of a web app with an interactive map. We represent our wildfire as a MDP and determine how at risk counties are based on the fire location(s).

How we built it

We split the project into 2 main parts: web app and AI

Website

Artificial Intelligence

  • Represent the wildfire as a MDP (Markov Decision Process)
    • States: Counties
    • Actions: Traversing Counties
    • Probability distribution: generated from wind data
    • Transition Model: generated from wind data
    • Reward function: Uniform for every county burned (prone to change if scaled up)
  • Use bellman equation to iterate through counties and propagate the fire
    • Utility values ranging between 0 and 1 represent how at risk a county is
    • Screenshot
    • Run until utility values reach equilibrium or until 100 iterations are run
    • Gamma = 0.8
  • Represent the map as a graph
    • Counties are nodes
    • Wind speeds are edges
    • Assign each county with a risk (for reward function)
    • Spawn fires on specific counties

Challenges we ran into

Our project has a pretty large scope. We needed to develop a model and integrate it with a web app. This required extensive knowledge on AWS utilities and crisp communication between team members. The machine learning portion of this hackathon was difficult as we had to decide on what type of model to use for the wildfire and how to assign reward and utility values.

Accomplishments that we're proud of

We were able to integrate the web app with the model really quickly. This was surprising since usually connecting the pieces together will have a lot of bugs. It was also Austin, Raaj, and Romuz's first hackathons and this was a fairly complex project compared to a standard web app.

What we learned

This hackathon was a first for many of us. This was the first time any of us had implemented a machine learning model and connected it to a web app.

This was my first time at a hackathon and I couldn't have asked for better teammates than Jerry, Raaj, and Romuz. I learned so much over the last two days about machine learning, data science, React, and working as a team to help tackle some of California's greatest challenges. - Austin Rivard

As a first-year student, I have learned a lot of new skill sets while working with this team. I was happy to be a member of such an agile team. I learned numerous of new concepts, such as working with AWS, writing algorithms, and the graph data structures. - Romuz Abdulhamidov

What's next for Arson

  • Scale up to entire California to generate a better map during wildfire season
  • Generate more accurate Reward values for each county burned
  • Incorporate type 2 rewards based on R(state, action)
    • Wildfire gets bigger as it burns more land
    • Wildfire gets smaller in the presence of firefighters
  • Automatically train and deploy models by integrating real-time data for wind and wildfires

Demo

Screenshot

Owner
Jerry Lee
software engineer
Jerry Lee
SNV calling pipeline developed explicitly to process individual or trio vcf files obtained from Illumina based pipeline (grch37/grch38).

SNV Pipeline SNV calling pipeline developed explicitly to process individual or trio vcf files obtained from Illumina based pipeline (grch37/grch38).

East Genomics 1 Nov 02, 2021
DaCe is a parallel programming framework that takes code in Python/NumPy and other programming languages

aCe - Data-Centric Parallel Programming Decoupling domain science from performance optimization. DaCe is a parallel programming framework that takes c

SPCL 330 Dec 30, 2022
Mining the Stack Overflow Developer Survey

Mining the Stack Overflow Developer Survey A prototype data mining application to compare the accuracy of decision tree and random forest regression m

1 Nov 16, 2021
Leverage Twitter API v2 to analyze tweet metrics such as impressions and profile clicks over time.

Tweetmetric Tweetmetric allows you to track various metrics on your most recent tweets, such as impressions, retweets and clicks on your profile. The

Mathis HAMMEL 29 Oct 18, 2022
Creating a statistical model to predict 10 year treasury yields

Predicting 10-Year Treasury Yields Intitially, I wanted to see if the volatility in the stock market, represented by the VIX index (data source), had

10 Oct 27, 2021
Data exploration done quick.

Pandas Tab Implementation of Stata's tabulate command in Pandas for extremely easy to type one-way and two-way tabulations. Support: Python 3.7 and 3.

W.D. 20 Aug 27, 2022
Package for decomposing EMG signals into motor unit firings, as used in Formento et al 2021.

EMGDecomp Package for decomposing EMG signals into motor unit firings, created for Formento et al 2021. Based heavily on Negro et al, 2016. Supports G

13 Nov 01, 2022
Very basic but functional Kakuro solver written in Python.

kakuro.py Very basic but functional Kakuro solver written in Python. It uses a reduction to exact set cover and Ali Assaf's elegant implementation of

Louis Abraham 4 Jan 15, 2022
Python reader for Linked Data in HDF5 files

Linked Data are becoming more popular for user-created metadata in HDF5 files.

The HDF Group 8 May 17, 2022
Data Analysis for First Year Laboratory at Imperial College, London.

Data Analysis for First Year Laboratory at Imperial College, London. For personal reference only, and to reference in lab reports and lab books.

Martin He 0 Aug 29, 2022
bigdata_analyse 大数据分析项目

bigdata_analyse 大数据分析项目 wish 采用不同的技术栈,通过对不同行业的数据集进行分析,期望达到以下目标: 了解不同领域的业务分析指标 深化数据处理、数据分析、数据可视化能力 增加大数据批处理、流处理的实践经验 增加数据挖掘的实践经验

Way 2.4k Dec 30, 2022
A Big Data ETL project in PySpark on the historical NYC Taxi Rides data

Processing NYC Taxi Data using PySpark ETL pipeline Description This is an project to extract, transform, and load large amount of data from NYC Taxi

Unnikrishnan 2 Dec 12, 2021
This is an example of how to automate Ridit Analysis for a dataset with large amount of questions and many item attributes

This is an example of how to automate Ridit Analysis for a dataset with large amount of questions and many item attributes

Ishan Hegde 1 Nov 17, 2021
Feature engineering and machine learning: together at last

Feature engineering and machine learning: together at last! Lambdo is a workflow engine which significantly simplifies data analysis by unifying featu

Alexandr Savinov 14 Sep 15, 2022
Single machine, multiple cards training; mix-precision training; DALI data loader.

Template Script Category Description Category script comparison script train.py, loader.py for single-machine-multiple-cards training train_DP.py, tra

2 Jun 27, 2022
Implementation in Python of the reliability measures such as Omega.

reliabiliPy Summary Simple implementation in Python of the [reliability](https://en.wikipedia.org/wiki/Reliability_(statistics) measures for surveys:

Rafael Valero Fernández 2 Apr 27, 2022
Retail-Sim is python package to easily create synthetic dataset of retaile store.

Retailer's Sale Data Simulation Retail-Sim is python package to easily create synthetic dataset of retaile store. Simulation Model Simulator consists

Corca AI 7 Sep 30, 2022
Dbt-core - dbt enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.

Dbt-core - dbt enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.

dbt Labs 6.3k Jan 08, 2023
NumPy aware dynamic Python compiler using LLVM

Numba A Just-In-Time Compiler for Numerical Functions in Python Numba is an open source, NumPy-aware optimizing compiler for Python sponsored by Anaco

Numba 8.2k Jan 07, 2023
Universal data analysis tools for atmospheric sciences

U_analysis Universal data analysis tools for atmospheric sciences Script written in python 3. This file defines multiple functions that can be used fo

Luis Ackermann 1 Oct 10, 2021