Making a Big Impact on Sustainability with Big Data from Security & Sustainability Forum
Aired on 9/21/2017
Issues in sustainability science are increasingly being addressed using “big data” and data analytics. Data rich modeling techniques can assist in improving systems thinking to integrate business operations, people, ecosystems and climate.
The result can be improved decision making, greener supply chains and optimization of business operations — all leading to increased corporate profits and important social benefits.
The ultimate goal of big data science is to foster economic development, improve social livelihoods, and enhance environmental quality. SSF, leaders from Chatmine Technologies and Boston University participated in a free webinar demonstrating the application of computational modelling of natural and social processes to identify patterns, trends, and associations that can inform sustainability decision making. The webinar was organized around five case studies focused on integrating multi-scale and multi-source data and applying spatial statistical techniques, artificial intelligence algorithms, and systems modeling to derive business insights and strategies.
The presentations are appropriate for a non-technical audience and include:
- Behavioral Correlations: Are hybrid or electric car drivers more likely to solarize their roofs? This project explores behavior and attitudinal data of some consumers in Massachusetts.
- Analyzing Flood Risk: Flood insurance is increasingly important for residential and commercial property owners. Flood risk is still mapped using USGS 100 year flood maps. These maps have to be completely updated and revised using new satellite data that can be analyzed to provide better risk probability profiles based on the International Panel on Climate Change (IPCC) models. This example reports on work for a commercial insurance company.
- Forensic Environmental Investigations Using Neural Networks: Urban sustainability includes protecting urban trees and forests. Panelists applied unsupervised neural networks to examine the impact of natural gas leaks caused by aging infrastructure that resulted in tree mortality in Boston.
- Predicting Malaria Hot Spots: Increasing temperatures in the highland regions of East Shoa in Ethiopia have led to increased incidence of malaria. Spatial statistical analysis, shown in this example, predicted the clusters or hot spots of malaria.
- Municipal Resilience Snapshots: Designing and implementing sustainability metrics for a neighborhood or town can provide a quick snapshot of its current or future social and natural resiliency, as illustrated in this example.
Panel:
Suchi Gopal, PhD is a professor at Boston University; her research interest is multidisciplinary dealing with spatial analysis and modeling, GIS, data mining and information visualization and artificial neural networks. She has applied spatial analysis to address a variety of problems in biology, environmental science, public health, and business.
Suchi is currently working on urban sustainability issues. She is also the CEO of Chatmine Technologies that specializes in big data analysis and business insights for industry, business and government clients, including the healthcare, technology, packaging, and financial sectors.
Joshua Pitts is a data scientist and software engineer, with a focus on integration of unique data sets to model complex systems. Recent work includes GIS-based environmental/climate modeling and visualization for the MacArthur Foundation, Conservation International, and the National Park Service.
Josh also serves as CTO of Chatmine Technologies, where he manages the big data analytical program.
