Artificial Intelligence in the wild — let’s look at a deeply unlikely yet effective AI use case



Original Source Here

Artificial Intelligence in the wild — let’s look at a deeply unlikely yet effective AI use case

5th June being world environment day, and having read about the functional extinction of the northern white Rhino, got me thinking on whether technology can, and has played a role in wildlife conservation.

I set out to find the crossroads between Artificial Intelligence and Wildlife conservation that has created a positive impact.

So who are the stakeholders?

Animals (duh!):

According to the World Wildlife Fund, vertebrate population has shrunk an average of 60 percent since the 1970s. And a recent UN global assessment found that we’re at risk of losing one million species to extinction, many of which may become extinct within the next decade.

Rangers/conservationists:

1 in 7 rangers have been seriously injured at work in the past 12 years by poachers.

871 rangers have lost their lives in the line of duty in the last 10 years.

Poachers:

The estimated value of illegal trade is 19 Billion USD per year!

Illegal wildlife poaching is organised crime, and what we need is an organised community and top notch technology to fight this crime.

How is artificial intelligence playing a role?

Just like how Netflix and google use AI to recommend new movies or predict your search results, we can use AI to predict the likelihood of poaching in protected forest areas. Let’s follow the steps involved:

· The 1st step to an artificial intelligence system is gathering data.

SMART( Spatial Monitoring And Reporting Tool) is a program that collects data from protected forests areas via aerial photos, ranger inputs etc and gives 3 sets of data:

1. Animals sightings

2. Locations of poachers and snare sightings (snares are traps set by poachers to catch animals)

3. Where the rangers have been patrolling

· The 2nd step is Analysis, modelling & prediction/recommendations: Now how can AI learn from the above sets and create AI/ML models to predict where the rangers need to patrol to increase possibility of finding poachers and snares?

Just like how Google maps uses AI to find the best possible route every day to reach your destination.

An AI/ML solution called PAWS (Protection Assistant Wildlife Security) gives the best possible route the rangers should take in order to approach and intervene in poachers’ activities, with incredible accuracy.

This is especially helpful when there are large areas of protected forests to be patrolled and limited number of rangers, as the rangers can use all the possible aid for them to be effective and optimized.

Now let’s look at the layers of data at work to give predictions?

LAYER 1: Land data: topography, weather , roads/paths

LAYER 2: Animal sightings , poacher sightings, ranger patrolling

OUTPUT Predictions:

1. Heatmaps of low risk and high risk areas (of finding poachers)

2. Suggested patrol routes based on the risk

Result:

This resulted in a 5x increase in the number of poachers and snares found, therefore saving animals, who are specially endangered.

Impact:

1. Anti-poaching programs gauge the health of specific species,

2. Local governments can use data to inform policies and create conservation measures.

3. Helps the way protected areas are managed

4. Empower local communities in conservation

5. Bring the best data closer to conservationists and decision makers

Even with many challenges ahead, engineers and researchers are hopeful that AI/ML can go a long way in creating significant impact in saving the endangered animals, plants and marine life of the world!

AI/ML

Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot

%d bloggers like this: