Can AI-Based Solutions Help Mitigate The Climate Change Crisis?


Artificial Intelligence (AI) has been assisted by tech firms and NGOs across the world to fight the climate change crisis. Gadgets 360 caught up with a few, including the team from the Sustainable Environment and Ecological Development Society (CEDS) – a New Delhi-based NGO – and IBM India to talk about their efforts to apply technology to mitigate the climate crisis. .

Although big tech companies are now moving to measures to become more sustainable (Apple And Facebook pledged to be carbon neutral by the end of the decade), much remains to be done, and this is one of the areas where artificial intelligence is making an impact.

With the United Nations Climate Change Conference beginning in Glasgow on 31 October, discussions on the global climate change crisis are again in the limelight. The 26th edition of the Conference of the Parties (COP26) will run till November 14 and will see global leaders, academic experts and activists gather to discuss how to control the rise in global temperatures.

But as world leaders develop policies and long-term plans, we spoke to innovating companies on the ground to see how they can help contribute to change.

Surviving Disasters Through Sunny Lives

SEEDS has developed Sunny Lives, an AI-powered disaster impact model that uses high-resolution satellite imagery to assess hazard risks at the ultra-local level. The Sunny Lives project has been executed in partnership with Microsoft and technology partner Rural, and is being supported under Microsoft’s global program ‘Artificial Intelligence for Humanitarian Action’.

Mridula Garg, who leads the Sunny Lives project at SEEDS, said Sunny Lives detects the footprints and then assigns them relative risk scores as a value of 1 to 5. Exposure based on geographic parameters such as slope and vegetation, and uses building classification as a proxy for the socio-economic vulnerability of residents. Garg said, the relative risk score given after tracing the building footprints is used by our disaster response teams to prioritize the families at highest risk.

During application to the impending cyclone, satellite imagery is obtained for the areas of interest which are selected based on the forecast path of the cyclone released by IMD. The Sunny Lives AI model is then run to generate risk scores for these sectors.

It was clear to the team at SEEDS that the type of building played an important role in predicting the impact of the disaster on it. For example, a concrete house and thatched-roof dwelling will face differences in impact from cyclones even when located next to each other. The model was developed out of a desire to code this knowledge so that disaster risk assessment could be broadly extended.

Microsoft’s data science team and tech partner Grammar used machine learning to automate the process of identifying habitats and their types. Satellite images of low income, highly dense and vulnerable settlements in India were used to identify 7 different categories of housing, including tarpaulin roofs, metal sheet roofs, double sided sloping tile roofs etc. are included.

The AI ​​model was trained on 15,000 buildings from low-income, highly dense and vulnerable settlements of Puri and Mumbai. 15,000 buildings were tagged to form the training dataset for the AI ​​Induction Model. A similar exercise is now being carried out for the cities of Dehradun and Gangtok as models are being adopted for earthquake risk assessment.

Sunny Lives was deployed extensively for the first time during Cyclone Yas in May 2021. The model was run for Puri in Odisha, based on which SEEDs reached out to over 1,000 families that were identified as high risk. Advice shared which outlines steps to be taken in case of evacuation and also suggests low cost measures

Garg said the post-disaster surveys have highlighted that 97 per cent of the households found the information useful and were able to reduce the damage and take pre-emptive measures during the cyclone. “In addition, we have recently concluded about 1,500 ground truthing surveys in Puri which will help in analyzing and further improving the accuracy of the model,” Garg said.

An AI model like Sunny Lives offers wide potential in urban geographies and is being adapted to multiple threats. Implementing the model at scale through collaboration is the next main focus for Seeds. “We have taken a lot of interest from several state government officials and are reaching out to many more people. Our approach is to integrate the use of models for climate change adaptation and disaster management in such a way that the hyper-local risk of communities is understood and their safety and resilience pathways can be put into practice,” said Garg.

Tech Firms’ Solution to Counting CO2

Major companies around the world have pledged to stop climate change. These companies are faced with the challenge of quantifying their emissions and figuring out the best way to mitigate the climate change crisis. In response, many tech firms have come up with a solution To help businesses prepare for and respond to climate risks.

salesforce The team built the Salesforce Sustainability Cloud with the mission of tracking emissions. stability cloud price is $4,000 (approximately Rs 3 lakh) per month. Microsoft is also previewing a tool for calculating emissions called Microsoft Cloud for Stability. They are aiming to make it available by the middle of 2022.

ibm It also recently brought out a suite of environmental intelligence software that uses AI to help organizations prepare for and respond to climate risks. The IBM team said the suite will help businesses that have deployed it to more easily assess their impact on the planet, and reduce the complexity of regulatory compliance and reporting.

Gargi Dasgupta, Director, IBM Research, India, said, “We wanted to make it easier for companies to learn about the risks affecting management and their business operations, and to act differently to mitigate risks.”

The suite uses existing weather data from a variety of sources to collect and compile the data. IBM said in its blog post That suite is a software-as-a-service (SaaS) solution designed to help organizations monitor disruptive environmental conditions, predict potential impacts of climate change, prioritize mitigation and response efforts, and measure and report environmental initiatives. is designed to do. The IBM Environmental Intelligence Suite uses AI-powered innovations from IBM Research.

Shantanu Godbole, technical lead of IBM’s global research team, said that in assessing how the technology would affect climate change, they focused on two areas – mitigation and adaptation. Mitigation works toward helping organizations meet their net zero carbon emissions goals, optimize their emissions, and make their business processes more sustainable.

Godbole said his team’s focus in terms of adaptation was to help businesses adapt to extreme weather conditions. “Weather is predicted one to two weeks into the future. There is no data available on a six-month or three-year scale down the line. This is a horizon that is a significant opportunity area from a planning and decision-making point of view. We think that enterprises need technology to help them make decisions at that time,” Godbole said.

Affiliate links may be generated automatically – see our moral statement For details.