The finalists for the 2019 Con X Tech Prize
From pig-finding thermal drones to hi-tech frog refuges
The Con X Tech Prize is a global competition that provides funding for project teams with a bold conservation idea that are preparing their first prototype.
The goal of Conservation X Labs’ competition is to build the ecosystem of early-stage conservation technology products and solutions, and supporting growing teams and ideas from around the world. Selected teams receive seed grants ($3,500.00) to support their work over a ten-week period. At the close of the prototyping period, one team is awarded the Grand Prize ($20,000.00).
Funding a working prototype is just the beginning. It can help a team validate a project idea, launch a successful crowdfunding campaign, net a strategic partnership, or even raise a successful seed investment.
Here is a roundup of some of the Fourth Wave 2019 finalists. (Copy below is from the finalists themselves and has not been independently verified, nor does it necessarily reflect EDF’s positions.)
Elephant Biologger Project
African elephants are threatened by habitat loss for agriculture and development, poaching, and climate change. The Reteti Elephant Sanctuary rescues between five and ten orphaned elephant calves per year which they release at age three. The calves then need to be tracked and their health monitored. The current and widely used approach for radio and GPS telemetry with elephants wearing collared tracking devices are deemed unsafe or short-term in the view of Retiti, as their juvenile elephants will grow until age 15–20.
The Elephant Biologger Project seeks to develop an affordable implantable biologger solution to monitor juvenile elephants re-wilded to new non-native herds. This biologer will continue to function as the elephant grows (rather than a collar, which will constrict the neck). Each of the biologgers will uplink location information via Low Power Wide Area Networks (LPWAN) to terrestrial base stations, both fixed and dynamic, which will transmit the data to the cloud, over GSM network, wifi, or satellite.
Currently, there isn’t a highly accurate Fish Recognition artificial intelligence technology that is open source and that focuses on immediate fish identification worldwide. Fisheries scientists need effective management in conservation efforts and this includes correct fish identification that is less costly and time-consuming than current human-dependent methods.
Fishial.ai will have the ability to reduce human error, sampler bias and to minimize resources to conduct fisheries management efforts. Fisheries agencies may also implement the fishia.ai model as a training source for biologist and enforcement officers. The open source model from fishial.ai can also support research efforts conducted by academia lead research teams if it is implemented into a platform of their choice, or they can build a platform around the model. The fishial.ai model can be used in the field to identify fish species as they are collected, saving hours of lab time in identifying specimens. Once back in the lab the images can be reviewed by a technician on a smart device or computer. The images collected from the field can also be used as a source for training and continuing education within the lab. Commercial use of fishial.ai can include apps for recreational anglers that help reduce misidentification, and to novel approaches to solve conservation woes.
Remote Amphibian Refuges
When working with frogs researchers discover that finding them is hard. Also, field research, especially in developing countries, faces severe restraints when it comes to resources, so they must be as efficient as possible.
This team of finalists modified the use of PVC tubes or bamboo refuges to a more technological solution, adding a small speaker that will play reproductive calls which will attract females of the species of interest or males that are looking to maintain their territories. Also, they incorporated an Arduino unit with a motion, temperature and humidity sensors that will help notify the researchers that the refuges have caught a frog with a notification message that is sent directly to cellphones. It is kept inside a metal compartment that is harmless to the frogs and keeps the circuit dry. The tube will contain a pool where the frog can rehydrate and a mesh that allows researchers to look inside the refuge. A couple of prototypes have been equipped with cameras with motion sensors to photograph possible catches. The refuges can be placed in the ground or strung up in trees, allowing researchers to target several microhabitats that might be preferred by different species.
Seacology Deter, Detect+Detain
It is not cost-effective to police offshore Marine Protected Areas, so they are mostly not protected at all. Patrol boats ($22m to buy, thousands of dollars a day to operate) and aircraft ($140m to buy, $18,000 per hour to operate) are too expensive for developing nations, and satellite-based systems have important gaps which hide the problems. All nations with large sea areas to protect need a cost-effective solution.
Seacology will operate a constellation of buoys of two types: Deter buoys will broadcast on Marine VHF, warning fishers they are entering a protected area and face confiscation and jail if they fish here. They will also flash high-intensity red and blue lights for fishermen without VHF. This will be backed up with public relations in the fishers’ home countries warning of the effective new system, perhaps showing the “perp walk” for captured vessel skippers.
Detect buoys will use a phased array of passive sonar hydrophones; the on-board processor will classify fishing boats by the sounds of their engines and gear over time. Once a contact has been classified as fishing, the Detect buoy will send an short encoded message to a satellite, which will relay it to a cloud service. This data will be cross-referenced with other data sources such as GlobalFishingWatch, Eyes on the Sea, potentially local VMS. Actionable alerts will be provided to the local enforcement agency including estimated position (through triangulation of two buoys by the cloud service, or by a single buoy estimating distance by fishing activity pattern).
North Atlantic Right Whales (NARW) are facing extinction largely because they get entangled in fishing gear, including lobster trap lines. These lines, which connect a buoy at the surface to traps hundreds of feet down on the seafloor, are so long that whales swimming through get caught. The NARW population has only 500 members remaining worldwide; entanglement not only kills whales, but also renders female survivors less likely to reproduce. New England is both a lobster fishing mecca and one of the right whale’s primary habitats. If we are going to avoid the extinction of the NARWs, the industry urgently needs a solution that fishermen, regulators, and conservationists can agree on. A solution to the problem of NARW entanglements in New England would inform scaled development to prevent whale-entanglement worldwide.
LobsterLift is a lineless, self-surfacing, modular lobster trap retrieval system. Traps utilizing LobsterLift sit entirely on the seafloor without requiring a line to the surface, and are raised when needed, thus eliminating the danger of whale entanglement. To retrieve a trawl (set of traps), a fisherman sends an acoustic signal from a tracker on the boat to a module attached to the trawl. The module then releases air from a tank to inflate an attached balloon. The balloon increases in size until it can float the trawl to the surface where the traps are retrieved, removed of their catch, and re-baited.
In addition to helping to protect the endangered NARW, the LobsterLift provides several other benefits compared to existing techniques. The tracker on the boat can gauge signal strength from the module to triangulate its specific location. Locations plotted on a mobile application allow fishermen to recover their traps more easily than with line-based techniques.
Find that plant
Hawaii (and much of the world) is losing the war against invasive species. As a result, native ecosystems, cultural heritage, and environmental services are all at risk. In Hawaii, existing approaches, including aerial herbicide applications via manned aviation and exhausting and often dangerous work on the ground by field crews, have been used for decades with mixed and often disappointing results.
New technologies, including drones and miniaturized sensors, hold promise for expanding our surveillance capabilities, but have yet to put a real dent in the encroaching spread of these aggressive invaders. One of the biggest bottlenecks currently associated with using very high resolution drone imagery to detect individual invasive plant targets in high-value areas is the need for trained human analysts to manually scan each individual image. While effective, this is time-consuming and tedious work, given that drone surveys produce 1000s of photos for relatively small areas (200–500 acres). Computer vision and machine learning hold great promise for automating this process, and we have begun to have some success with training computer algorithms to detect various plants of interest.
Technology alone will not solve Hawaii’s worsening invasive species problem, but effective and targeted technology can be leveraged to expand the impacts of the limited budgets and personnel resources we currently have dedicated to this important issue.
To solve the bottleneck problem associated with processing 1000s of high resolution images to detect individual plant targets within a sea of similar-looking vegetation, Find that plant is developing a flexible machine learning algorithm that will: automatically scan through raw geo-tagged imagery and detect individual plants of interest with a high degree of accuracy, convert the detected plants’ raw image pixel coordinates into real-world geographic coordinates within a zone of expected positional uncertainty, and produce a list and GIS layer of all the resulting coordinates for management decisions
Pig-finding Thermal Drones
The Galapagos Islands most iconic inhabitants and name givers of the Islands, Galapagos giant tortoises, have seen a 90% reduction in population over the last 180 years and are projected to go extinct in the wild if no actions are taken. This is because feral pigs find and dig out tortoise nests destroying entire generations of Galapagos tortoises. A recent pilot study found that 50% of tortoise nests were destroyed by pigs. During the nesting season, park rangers go through challenging terrain to find and kill pigs and identify tortoise nests, which are protected with wire mesh. This is an arduous task that involves thousands of man hours annually and makes protecting nests a race against time (or against pigs). If we want to ensure the survival of these iconic species (which are critically important for Galapagos due to their ecosystem services and for tourism), we must know where and when feral pigs are close to tortoise nesting sites and find tortoise nests before the pigs do.
This finalist plans to attach a thermal camera to a drone so we can find feral pigs and tortoise nesting sites from the air. Pigs, normally shy and hard to find by foot, will be found from above by their thermal signature. Specifically, we will use computer vision and machine learning techniques to recognize, count, and identify pigs and tortoise nests by thermal signature. It would take a team of five park rangers several days to identify tortoise nests, but by combining our algorithm with drone imaging this could be done in hours. We will share locations of pigs and nests with park rangers daily during the tortoise nesting seasons. Rangers will then go to marked nesting coordinates and protect nests.
Blockchain Ecosystem Payments
Payments for Ecosystem Services (PES) programs have recently become an important tool in environmental governance. In a typical program, landowners receive payments to manage ecosystems. Payments are usually made by governments or by interested private sector stakeholders. A prominent example of PES are carbon sequestration payments, which incentivize forest owners to keep forests intact to store the sequestrated CO2 Another example are wildlife conservation incentive payments, which reward landowners for maintaining biodiversity. In developing countries, where some of the most pressing environmental issues are currently found, PES programs suffer from a lack of formal institutions. If the rule of law is not upheld and the banking infrastructure is poor, PES programs can corrupt and the payments fail to reach the landowners.
This finalist will build a blockchain-based application that makes PES more efficient and effective. For the first time, the application will make the link between blockchain smart contracts and remote sensing algorithms that detect land-use change. In addition to the back end, they will develop a convenient front end to make the application accessible for the broader public.
In order to illustrate the potential of their proof-of-concept they want to implement a prototype using a real-world example and are working with the WWF Namibia, which administers a PES program that rewards communities for maintaining the integrity of elephant corridors. The prototype will monitor the state of the corridors and execute periodical smart contract payments to the community if the corridor remains intact.