1. General

Category

Category

Environment

2. Project Details

Company or Institution

Conservation X Labs (CXL)

Project

The Sentinel System

General description of the AI solution

Technological advances in environmental monitoring have enhanced our understanding of the world, but there is no solution that delivers real-time information that can be acted on from anywhere. Advancing artificial intelligence (AI) technologies and machine learning (ML) for monitoring our planet’s most sensitive habitats can address this problem; however, there are enormous technical barriers. The tools that capture information from the environment are typically ineffective, expensive, and time-consuming. Environmental protection deserves technologies that are intuitive and will scale rapidly to expand conservation impact.

In response to this need, Conservation X Labs (CXL) developed the Sentinel System, a hardware and software AI platform that turns environmental sensors (e.g. camera traps, acoustic monitors, hydrophones) into smart devices that automatically detect rare, vulnerable, or invasive species and identify poachers or disease. Users can capture real-time information for research, wildlife crime management, and environmental protection without reliance on the cloud or manual data collection. By processing data when it is captured and filtering critical knowledge for low-bandwidth communication, users receive valuable information in the form of near-instant messaging (i.e. SMS messages).

Before the Sentinel, there had never been a method for creating, running, or deploying a machine learning model with little or no technical expertise. Sentinel’s online platform allows users to browse and create AI models that fit their needs, much like Apple’s App Store. The Sentinel is the only solution of its kind that provides an affordable, easy-to-use monitoring platform that transforms existing systems.

The Sentinel has already been selected for use in a variety of unique projects around the world, including identifying rare jaguars in Costa Rica, informing wildlife crime officers of suspicious behavior in South Africa, and monitoring gorilla behavior in the Congo.

Website

https://conservationxlabs.com/sentinel

Organisation

Conservation X Labs (CXL)

3. Aspects

Excellence and Scientific Quality: Please detail the improvements made by the nominee or the nominees’ team or yourself if your applying for the award, and why they have been a success.

Conservation X Labs (CXL) developed the Sentinel System to enhance existing networks of camera traps and acoustic monitors for environmental sensing. The technology does not replace the functionality of existing environmental sensors but instead replaces a single component – the memory card. The Sentinel transforms these devices into self-contained platforms that run AI algorithms on site. This approach allows Sentinel users to collect information as it is captured as opposed to waiting until someone can retrieve the memory cards. The Sentinel also automatically and immediately sorts, processes, and filters massive amounts of data as it is captured. As a result, Sentinel eliminates the costly burdens of infrastructure, maintenance, and data management.

As data is processed, the Sentinel System instantly informs users of significant events. These insights are delivered through email, SMS messages, or other forms of instant messaging. With this combination of edge-AI and global connectivity, the Sentinel makes real-time access to mission-critical data affordable and efficient and frees highly-trained staff resources to act on information.

The Sentinel dashboard allows users to manage their devices remotely, browse models that suit their needs, and immediately run algorithms on their devices. Most importantly, users do not need coding or AI knowledge to set up, use, or manage the system, making it accessible to environmentalists. This application of accessible AI models is a significant advancement to commonplace use of AI in environmental monitoring.

The team is in the process of filing a provisional patent for the Sentinel hardware, and development of the system currently lies between TRL 5-6, with preliminary field demonstrations conducted using pre-production units. The Sentinel System has been fielded in trials with our partners at The Nature Conservancy and at properties near CXL’s headquarters in Washington, DC. We are currently preparing larger-scale deployments in Costa Rica and southern Africa.

Scaling of impact to SDGs: Please detail how many citizens/communities and/or researchers/businesses this has had or can have a positive impact on, including particular groups where applicable and to what extent.

The Sentinel System empowers users to act on data in real-time through the democratization of access to AI technologies for environmental monitoring. Our scheduled deployments of over 440 devices in the coming months will support over 100 researchers across three continents and six countries.

The Sentinel ensures that our ability to collect massive quantities of environmental data from our lands and oceans results in an equally significant yet affordable ability to make informed, timely decisions based on that data. By democratizing access to AI capabilities, the system allows environmentalists and others to better understand these environments in real-time and make effective, data-informed decisions on policies, protection, and resource utilization.
Conservation X Labs is an innovation company that applies the tools of innovation to environmental and conservation issues. The Sentinel development team has prepared for upcoming deployments of the platform to ensure that impact is understood by users and incorporated into the ongoing product development. The online platform is designed to consolidate data across deployments of the system to improve understanding of global environmental trends and patterns as well as use and performance of the distributed network of devices.

The Sentinel web platform allows users to browse the existing library of AI models, developed by global artificial intelligence (AI) and environmental experts, that may already suit their needs. Should a custom model be needed, users can also create tailored algorithms within minutes involving no coding by leveraging their own data and/or the millions of cataloged data points in the Sentinel System library.

Scaling of AI solution: Please detail what proof of concept or implementations can you show now in terms of its efficacy and how the solution can be scaled to provide a global impact ad how realistic that scaling is.

CXL plans deployments of over 440 devices in the next six months in partnership with 11 testing organizations from the United States, South Africa, Mozambique, Zimbabwe, the Democratic Republic of the Congo, and Costa Rica. Through these early adopters, CXL will demonstrate that AI tools can reduce the costs of data analysis by over 90% while providing real-time notifications of remote events. Our goal is to deploy over 2,000 Sentinel devices by the end of 2022. This is a global opportunity to make AI tools and the power of environmental data accessible to everyone at a fraction of the cost.

As the Sentinel System is deployed globally, the online platform will be a hub for a community of conservationists, environmentalists, and experts to share models, research, and collaboratively improve the effectiveness of wildlife conservation. This extends to our in-country partners, building their capacity to adapt to new-found species, environments, and conservation actions. The real-time information captured by the Sentinel will help better inform environmentalists’ efforts to protect, restore and promote sustainable use of ecosystems, including mitigating the impacts of climate change.

The availability and use of AI models in an intuitive, user-friendly way can be easily scaled. The Sentinel has the ability to manage a suite of devices through the online platform and this will open the door for many communities who could benefit from AI technology but don't have access to it or face too high a technical barrier.

The Sentinel System automates the data collection and analysis processes so teams can focus on higher-level priorities and apply resources efficiently and effectively. This improved productivity enhances the emergence of future companies to develop AI solutions through our software pipeline, expands the accessibility to work with this technology, and supports an open-source AI ecosystem.

Ethical aspect: Please detail the way the solution addresses any of the main ethical aspects, including trustworthiness, bias, gender issues, etc.

Recognizing that AI learns what it is given, CXL uses datasets from trusted, local partners to reduce bias in the system. Both CXL and partners audit all datasets for multiple indicators of potential bias, reviewing the labeled dataset and model predictions. Furthermore, any data that is designated as high-risk (involving information on humans, or deployment of human resources, i.e. poaching-related) is fully audited under stringent standards. While available models are universally accessible, we also designate certain models as high-risk and restrict access to approved users who must abide by an ethical use agreement. CXL monitors these tools, access to these models, and the data that these models produce, and access can and will be revoked from abusers of the system. The Sentinel was created to make monitoring functionalities accessible to regions around the world that are critical to the environmental health of our planet but don't typically have access or expertise to utilize these cutting-edge technologies.

The democratization of access to powerful tools that help protect biodiversity is core to CXL’s mission. To minimize language barriers, the Sentinel user interface is graphical and multi-lingual and designed for use by non-technical personnel. Set up instructions and documentation adopt globally accepted norms for communicating common concepts in ways that span cultural and linguistic differences. Beyond user-facing elements, CXL also prioritized creating back-end (servers and cloud storage) infrastructure that provides high-quality service to global users, not just those in developed regions with access to high-speed, reliable internet resources. Throughout product development, CXL conducts user interviews and offers beta testing to indigenous peoples across localities worldwide where the Sentinel System is applicable for environmental restoration efforts and research.