Portfolio News

Simile: Leveraging AI and Open-Source Technologies to Revolutionize Flood Early Warning Systems in the Asia-Pacific

Similie Data Science+AI Timor-Leste

May 22 , 2024

Data Science+AI

Similie

Timor-Leste

Company Details

Amount invested $103,000 USD Funding Status active early period Founded in 2016 by Adam Smith & Craig McVeigh

Mid-investment update: Similie

UNICEF Venture Fund is featuring members of its Climate Action Cohort. The company is now six-months into a year-long investment period and shares an overview of their solution, progress, and next steps.

Tell us more about Similie.

Simile is a member of UNICEF Venture Fund’s 2023 Climate Action Cohort. Founded in Timor-Leste, Simile understands firsthand the impact that annual flash flooding has on communities throughout the Asia-Pacific region. The loss of property and livelihoods, decreased agricultural productivity, interrupted access to health and education services, and food insecurity caused by flooding threaten an already struggling economy. Existing solutions, like early warning systems and conventional hydrological modeling, are expensive, highly technical, and often require large sets of historical environmental data, making it difficult for communities and governments to access these life-saving technologies.

Simile recognized this gap in the early warning system (EWS) market and leveraged open-source technologies to develop and deploy their end-to-end EWS for emerging markets. Simile’s EWS collects data at the community level from a range of low-cost IoT sensors. This data is sent to their cloud-based platform, Parabl, where it is analyzed and set against adjustable thresholds, or modifiable data limits.

These thresholds can be set not only on Simile’s field-collected data (e.g., millimeters of rainfall or percentage of soil moisture) but also on any integrated third-party datasets (e.g., global forecasting models, existing/third-party monitoring networks). Once thresholds are met, Parabl sends out automatic alerts to users and communities through email, SMS, social media, and/or other IoT actions (such as sirens). Simile’s EWS is protecting over 300,000 people throughout Timor-Leste and has alerted the government and key international stakeholders of eight floods since deployment in 2021.

With support from the UNICEF Venture Fund, Simile will expand upon these successes by further developing their AI and machine learning (ML) capabilities to create a ML-informed risk assessment software framework. This framework will integrate into Parabl, giving stakeholders access to forecasting technologies that not only predict the likelihood of flood events but also help them understand the level of risk facing the lives and livelihoods of their people,

UNICEF’s investment helps us to develop our ground-breaking AI capabilities, and a platform to test and demonstrate its effectiveness to the global community.

Tell us more about your solution.

The deployment of effective flood early warning systems (EWS) requires reliable hydrometeorological data, including historical and real-time measurements of river levels and rainfall. This is a major challenge in emerging markets, as they often have limited access to historical and real-time hydrometeorological datasets. While global and regional forecasting services can enhance the efficiency of EWS, these services are typically designed for regional-level forecasts and may not meet the specific needs of national, district, or community-level forecasts.

To address this challenge, we incorporate frontier technologies such as artificial intelligence (AI) and machine learning (ML) into our EWS. These technologies enhance the accuracy and effectiveness of flood warnings, leading to better preparedness and response strategies. Specifically, we employ Long Short-Term Memory (LSTM) networks, which are widely used for weather forecasting, stock market predictions, and other applications requiring time-series predictions based on diverse data inputs. LSTM networks enable us to predict outcomes from continuous weather data using a wide range of inputs, allowing us to generate risk profiles based on real-time and predicted data. Additionally, we can test our trained models against simulated inputs to explore hypothetical conditions and "what if" scenarios that have not yet occurred.

To operationalize these models, we are developing an open-source ML-informed risk assessment software framework. This framework will integrate the ML model with demographic and GIS data to provide not only forecasted alerts of impending floods but also insights into the expected impact of disasters on specific communities.

The open-source nature of this software framework will enable other organizations to enhance their disaster preparedness and response capabilities. Developing this project as open source and "in the open" fosters collaboration with the broader climate risk reduction community, which may have different use cases from our own. These collaborations allow our initial vision to expand rapidly and efficiently, covering scenarios that we had not previously considered or were further along in our development roadmap. The collective knowledge of the wider community helps guide the software development process, making it more useful more quickly within an inclusive and positive community of stakeholders.

*A graph depicting plots of measured rainfall vs prediction from Similie's test data set.*

Our ML-based solutions will protect children by improving our time-to-event predictions, allowing us send life-saving messaging to impacted families sooner.

Tell us more about your team.

Simile is composed of 26 individuals who come from various backgrounds, cultures, and professional experiences. Our team includes experts in technology, design, climate change, hydrology, marketing, finance, and project management. This diversity in experiences and perspectives encourages innovative thinking and fosters a collaborative environment where everyone’s unique strengths contribute to our collective success.

What are your future plans and how can others support?

With investment from the UNICEF Venture Fund, we will focus on providing affordable, life-saving ML-powered technologies. Through this partnership, we aim to demonstrate measurable impact and attract the interest of key stakeholders throughout the region.

Our primary challenge currently lies in establishing connections with key decision-makers in climate change across the Asia-Pacific region. These vital connections are crucial for the success and widespread adoption of our solution. Through the Venture Fund’s mentorship program, we will collaborate with mentors to scale and grow our solution into other countries across the region. Additionally, we are seeking support in the form of introductions or connections to influential stakeholders, policymakers, or organizations specializing in climate initiatives throughout the region.

Interested to learn more about Similie? Visit their website or follow Similie on Facebook, Twitter, Instagram, and LinkedIn. Get in contact with the team directly via email at info@similie.org.