What If… Skynet Could Help Us Fight Extinctions
The implementation of Artificial Intelligence and Machine Learning in biodiversity conservation
What has the media shown us about Artificial Intelligence (AI)?
I’m a big fan of sci-fi. Almost everything involved with this culture fascinates me. Just not long ago, I decided to revisit an old classic of modern gaming, Mass Effect, the original trilogy, and replaying it got me thinking, why is AI depicted most of the time as evil or villains?
Another remarkable example of this is one of my favorite movies of all time, The Terminator. In the movie, there’s a company named Cyberdyne Systems. That developed a super AI which is entrusted with many offensive capabilities to be the first line of defense in America if the need arises. This AI developed a new order of intelligence that made itself aware. This evolution brought with it a different implementation of its instructions, and with it the decimation of the human race through nuclear war.
Both Mass Effect and The Terminator in a sense hit the same theme (human extinction) but with different outcomes. In Mass Effect, the selective “extinction” of advanced species, gave place to new species to take their place in the galaxy to be harvested and transformed as well in an infinite cycle. While in The Terminator, the total annihilation of humans comes through the interpretation of a machine that, to protect some humans, must identify threats and eliminate them. But AI falls into the ironic paradox where the biggest threat to humanity is humans themselves.
The constant theme of humankind/organics vs machines is quite recurrent in sci-fi. But what brings up this conception of machines taking over the Earth? and should we fear our new overlords? why is the media boarding these kind of plots? could we say in a way this is a form to reflect the problems that exist in our societies? should technology be our new nemesis to be vanquished? or should we see it as our greatest asset?
But what is an AI?
To address this question we need to keep in mind that the answer will not be an easy one, mostly because several answers have arisen in the last decades thanks to the advances made in this field, this adds layer upon layer to its complexity. In its purest form, is a field, which combines computer science and robust datasets, to enable problem-solving. It also encompasses sub-fields of machine learning and deep learning, which are frequently mentioned in conjunction with artificial intelligence. These disciplines are comprised of AI algorithms that seek to create expert systems that make predictions or classifications based on input data [1]. Suffice to add that it’s deeply intertwined with the fields of Machine Learning at a higher level, being the last a subfield within it. The implementation of this technology has a wide range that goes from robotics, data mining to biometric recognition and game theory, with many steps in between, so in theory AI could be implemented in many other fields.
AI for biological conservation
The application of AI to biological conservation might sound like avant-garde research and application field, especially considering both are completely different fields. There are several examples of how this has been implemented. For example, the repeated and strategic interaction between those who protect resources and those who seek to attack or exploit resources can be modeled using game theory as a repeated game. Through predictive analytics, the effort focuses on predicting where adversaries (e.g., poachers) will strike, then analytics work provides recommendations to defenders (e.g., rangers) to conduct strategic, randomized patrols. These analytics can be supported using machine learning [2, 3, 4].
Monitoring with Drones is being increasingly used in conservation to tackle the illegal poaching of animals. An important aspect of using drones for this purpose is establishing the technological and the environmental factors that increase the chances of success when detecting poachers. The efficacy of machine-learning for automated detection. In an experimental setting with voluntary test subjects, various factors were tested for their effect on detection probability: camera type (visible spectrum, RGB, and thermal infrared, TIR), time of day, camera angle, canopy density, and walking/stationary test subject probability of detection decreased with increasing vegetation cover. Machine-learning software had a successful detection probability, however it produced nearly five times more false positives than manual analysis. Manual analysis, however, produced 2.5 times more false negatives than automated detection. Despite manual analysis producing more true positive detections than automated detection the automated software gives promising successful results and the advantages of automated methods over manual analysis make it a promising tool with the potential to be successfully incorporated into anti-poaching strategies [5].
Besides, monitoring now could be done in real-time; historically scientists have long used camera traps to help them track and better understand the ecosystem’s health and biodiversity of wildlife in remote areas. These traps are set up and left for weeks on end where they flash a picture whenever an animal walks by. Now, AI is being used to classify these animals in real-time, to detect people or poachers in restricted spaces, identify individual animals, it also could be used to pick up acoustics from the environment, recording everything going on around it, including the sounds from different animal vocalization to the sound of chainsaws, gunshots, and motor vehicles [6].
Training an AI is also an area of opportunity through migratory patterns, using GPS trackers. AI algorithms can learn and predict an animals’ migratory pattern in order to learn how to best implement a conservation plan. Understanding where animals travel, scientists and people involved in conservation can better manage land and resources. With most of these tools available, the deployment of rangers would be easier when required but more importantly, decision making and plan implementations would be better underpinned with real-time data [6].
Even though the media sometimes depicts AI as our new rulers or our destroyers in reality it might be the other way around it. Is a fact that artificial intelligence is here to stay and we find it in everything we do in our day to day, we should learn from it and adapt and look for new alternatives that add more value to us as a society instead of fighting change, every time is a new opportunity to improve us and to protect everything that has an intrinsic value around us. It is only through our connections with other species and the environment that we will extend our time as a species, in other words we should preserve for self preservation.
