A Low-Cost TinyML Model for Mosquito Detection in Resource-Constrained Environments
Gibson Kimutai, Anna Förster · 2023-09-06
This study proposes a low-cost IoT-based TinyML model that intelligently activates mosquito repellent only when an Anopheles mosquito is detected, using a 1D-CNN for efficient classification of mosquito wingbeat sounds, reducing energy waste and potential health risks.
Gibson Kimutai, Anna Förster. 2023-09-06. A Low-Cost TinyML Model for Mosquito Detection in Resource-Constrained Environments. https://dl.acm.org/doi/10.1145/3582515.3609514 (AI & Environment Resource Hub; record paper-155; collection snapshot 2026-09-15).
Classification and context
Included in the original Scientific Paper collection. Labels below are metadata based suggestions. They are not verified findings, claims of effectiveness, or endorsements.
A paper listing is not a quality assessment. Peer review and findings require source-level confirmation. Source link reachable · checked 2026-09-15. Source identity and required metadata verified. The import date is not the original date added.
The abstract argues that policy debates about “sustainable AI” are stuck in an overly simplistic binary, AI as both an environmental threat and a tool for ecological transition, which leads to shallow regulatory approaches focused mostly on energy reporting. Drawing on law-and-technology scholarship, the authors show how technological determinism, exceptionalism, and regulatory solutionism distort the debate, and they propose reframing regulation around the socio-economic drivers and power dynamics of AI development rather than the technology itself.
SSRN
Shared topics: Cross-cutting sustainability; Energy and electricity; Biodiversity and ecosystems
This article examines how advanced digitalization and AI can enhance spatial energy planning and environmental assessments in Austria, offering solutions to data deficiencies that currently hinder biodiversity-friendly renewable energy transitions.
IAIA
Shared topics: Cross-cutting sustainability; Energy and electricity; Biodiversity and ecosystems
AI and ML optimize optoelectronic systems for sustainability by enhancing energy efficiency, renewable energy harvesting, environmental monitoring, and smart cities while also advancing ocean optics and photonics for marine ecosystem monitoring and climate change mitigation.
Library Progress International
Shared topics: Cross-cutting sustainability; Energy and electricity; Biodiversity and ecosystems
Conference held on the 19th of February 2026, organised by the Veolia Institute, hosted at the Collège des Bernardins, on the role of AI for the main environmental challenges. This event followed the joint publication of our last report, coproduced with Microsoft, called "AI for Energy, Water and Waste Management". Our experts explored the potential benefits of AI for the ecological transition in relation to concerns raised by its carbon footprint and growing energy, water, and precious metal requirements.
