How is AI used in Aquaculture?
Aquaculture is the breeding and harvesting of aquatic creatures. We’ll talk about companies that focus on fishes. The usage of AI in aquaculture has streamlined and expedited the daily tasks of fish farmers.
Usage of AI in Farms:
Estimate fish population:
Farmers will record videos of fish swimming across a net, with a white canvas underneath. The videos will then be ran on a software for the AI to detect and estimate the number of fishes for the farmers.
Estimate the number of harvested fishes:
Farmers will first need to lay out the harvests. Then, they have to open the fish detection app, take a photo/video or select one from their gallery, and let the app run. The AI algorithm will count the fishes for them.
With AI, farmers now have a modern and innovative tool that helps with their farm operations. This technology enhances accuracy, efficiency and promotes sustainability & responsible fish farming practices.
Why is AI used in Aquaculture?
The use of AI to count fish reduces farmer’s reliance of manual labour for fish counting tasks. It also saves their valuable time and effort. In turn, farmers can redirect their attention towards other essential farm activities. This reduces labour costs and enhances efficiency and productivity in farm operations.
In the long run, the benefits that farmers get far outweigh the cost of purchasing a fish counting AI system.
AI Automation of the Fish Counting Process
Farmers used to do manual fish counting. It was time-consuming, labour intensive and prone to errors. This led to inaccurate fish population or harvest estimates.
With AI, the fish counting process is pretty much automated as AI will be the one counting the fishes for them and that the farmers do not need to do much during this process. These farmers also gain more reliable results compared to traditional methods.
Contactless & Quicker Process
Implementing AI for fish counting has increased the speed of obtaining results. The need for physical contact also minimizes since AI can track and identify each fish without any physical contact. It reduces stress & the risk of harm to the fish, leading to a quick and less disruptive fish counting process.
Larger Customer Base & Positive Reputation
By using AI, farmers can showcase their commitment to sustainable and high-quality practices. It also reflects a proactive approach towards minimizing environmental impact and resource wastage. This helps in attracting a larger customer base and fostering a positive reputation in the market.
Accurate Stock Management
AI fish counting allows farmers to improve fish stock management accuracy. Farmers can account for all fish populations within their farms. This helps in making informed decisions on their stocks and harvests. It also improves farm productivity and profitability.
What has MWI done to help?
With MWI’s knowledge and skills, we understand that using AI in aquaculture is important. We also acknowledge the challenges and limitations that farmers face. To address these needs, we have taken the initiative to develop an AI fish counting model from scratch for fish farm businesses to use. Even MWI’s sister company, The Fish Farmer, uses our AI model to assess its fish population and harvest.
There are a couple of methods but we are only going to name and discuss a few here.
Hand/Manual Counting of Harvests
Fish farmers would count the fish one by one. This method needed a lot of time and effort, especially in large farms with high number of fish harvests. It is also more prone to human errors.
The use of this method resulted in inaccurate estimates and impact resource management decisions. This in turn affected the productivity on the farm.
Visual Observation of Live Fishes
Farmers will stand by the pond and observe the fishes, to gauge the number of fish present. They draw conclusions based on their judgement and expertise. This method is simple, inexpensive and based on farmer observation skills and attentiveness. But, challenges arise when fish swim in schools or overlap one another. It makes it challenging to count each individual fish.
Mark-Recapture of Live Fishes
Farmers fish for a certain number of fishes and mark them before releasing them back into the pond. After a period of time, farmers will fish again. They will then examine them for the presence of markings. To estimate the total population size, farmers will compare the proportion of marked fish in the second sample to the first round of marked population.
Farmers use tags or dye to keep the fish marks intact when they recapture them. This method is pretty accurate for estimating fish population size. But, there are also limitations to this. There is a possibility that the fish may lose their tags/dye marks when recaptured. It would make it difficult to identify the marked fishes during the second stage.
Working with The Fish Farmer, MWI employs vision AI in aquaculture in Singapore to count fish population with Object Detection and Tracking Algorithm.
Object Detection is the process of identifying and localizing objects of interest in an image or video frame.
It has two primary tasks:
(a) object localization, which determines the precise location of an object within an image, typically through bounding boxes, and;
(b) object classification, which assigns a label or category to the detected object.
Object Tracking is the process of locating and tracking objects in a video or image sequence. It is the detection of the object in each frame of the video and determining its position, size, and motion. There are several popular algorithms available. For this exercise, we use State-of-the-Art (SOTA) YOLOv5, YOLOv8, YOLO-NAS technologies.
Custom AI Model
This part of the blog gives an overview of how the fish counting vision AI model works from a layman’s perspective. Let’s begin.
At a high level, there are 3 steps in creating a custom AI model to do fish counting. We call these steps; training, validation and testing. This process is iterative in nature. More training, validation, and testing lead to a more accurate model.
1. Training Of Computer Vision AI Model
Imagine you are teaching a child to know the alphabets using flashcards. You would show him many variations of each alphabet. There will be variations of colour, size, shape, orientation and more. Showing many different versions of letters helps the child learn what each letter is made of. This is AI at its very core.
In this example, the “flashcards” or dataset will be the fishes in the local fish farm. Fish comes in varying sizes, colours, shapes, and have unique behaviours in different lighting and water conditions. More images of these fish in various states improves the model’s fish prediction accuracy. Training is the term used to describe the process of teaching the AI algorithm (the ‘brain’) to identify a fish.
2. Validation of Computer Vision AI model
Training alone is not enough. A child may have a superb memory and know each flashcard by heart without knowing the subject matter. The next step is validation. What a past year exam paper reveals about a student’s ability is what validation does to an AI model. During validation, we put the model through previously unseen data (“past years’ exam papers”). We will then compile the results. How well the child scores will give us a sign of how much he knows his subject beyond mere memory. If the model has high mAP (‘score’) for training but low mAP for validation, it is a sign that the model has not learnt and is memorising the ‘flashcard’. In AI lingo, the model is not a generalised model. This meant that there is a need to have more training with different variations. Now, the entire cycle repeats itself.
3. Testing of Computer Vision AI model
The real test of a child’s ability is when he finally sits for his examination in school. The test papers are completely unknown to him beforehand. During this time, the real test of his knowledge (or lack of) reveals itself. This process is called testing of the AI model. In general, a high mAP for validation will show a high mAP for testing.
These three steps outline the creation process of the AI in aquaculture.