Summary
- One of the largest welfare issues affecting farmed fish is poor water quality. Fish Welfare Initiative works to address this issue for these animals in India, via our farm program.
- The main limitation of our program right now is its scalability: We currently visit every farm individually to take measurements and provide corrective actions. Because of this, we are investigating remote sensing technology, particularly satellite imagery (and also exploring the use of drones).
- To further develop this tech, we launched an innovation challenge, in which we will pay up to $10K to the party that can predict water quality values using satellite-provided data above a certain degree of accuracy.
- How you can help: We think it's possible that individuals, using publicly available data (e.g.) could develop models of sufficient accuracy. Experience with remote sensing, machine learning, and statistical modeling could all be helpful here. Feel free to leave a comment or contact us if you're interested!
We recently posted more about this on our blog. The following is copied from that post:
The Problem: Limitations of Our Farmer Program
In FWI’s current main program, the Alliance for Responsible Aquaculture (ARA), field teams collect water quality data from member farms. If critical water quality parameters indicate that fish may be exposed to poor conditions, the field teams provide farmers with recommendations for corrective actions.
The current ARA model requires FWI staff to physically visit fish farms to measure water quality. The scalability of this model is limited by its dependency on in-field measurements which caps the number of farms FWI staff can visit each day. The limits to scalability also reduce the overall impact and cost-effectiveness of the program and we therefore want to determine ways to assess water quality without intensive in-field presence.
The Proposed Solution: Satellite-Based Remote-Sensing
Monitoring water quality using satellites may be one opportunity to remotely assess critical parameters and improve the scalability and impact of the ARA. Remotely monitoring water quality would allow water quality data collection from member farms more frequently and with lower resource input. And with that we could identify more instances where fish welfare is compromised. This technology also offers a potential mechanism to support many more farms, helping to cost-effectively scale the program.
While we have previously undertaken a project to explore the potential for remote-sensing water quality in aquaculture farms, our efforts were unable to provide models that matched our needs. However, we believe that the potential of this technology is so exciting and transformative for our programming, that it warrants further investigation. To boost our chances of success, we are launching an Innovation Challenge.
The Innovation Challenge
We are interested in a partnership with an entity who can successfully show that they have models matching our needs to leverage satellite technology to help scale our program and improve the welfare of millions of fishes.
We are seeking interested parties to either:
- develop new models allowing us to remotely monitor key water quality parameters at aquaculture farms in India through analysis of satellite data, or
- share existing models that can be utilised for our purposes.
We will provide a financial reward—up to USD 10,000—based on the outcomes of a validation process.
This innovation challenge is open to anyone. We encourage submissions from technology companies, academic institutions, non-profit organisations, individuals/groups, or any party that has relevant experience that can be applied to this challenge. Interested parties are invited to notify FWI that they have a model or models ready for validation by February 28th, 2025. The submission process does not require the submission of any code, merely a brief description of the model(s).
Full details of the Innovation Challenge can be found here. Please share this with anyone who could be interested in submitting a model. Thank you!
I used to work in remote sensing in a past life. I don't have much to say about the science of measuring water quality, but I do want to comment on the data collection question.
You mention satellites and drones. If you can get the info you need from existing satellite imagery that's great. To the extent that you need something more, I can recommend using manned aircraft over drones.
The world is well set-up for pilots to fly small aircraft. The type of drone you would need to cover a large area would have to be a very autonomous, fixed-wing aircraft. You don't need this. You can contract a pilot & plane for hundreds of $s an hour and cover a whole lot of ground per hour. I would bet you could survey the whole of India's fish farms annually for less than a single FTE in a western country working on drones.
Once you realize this, you might start thinking about other approaches than visible light. Can you identify substances that shouldn't be present in a humane fish farm and measure them with a spectrometer mounted on an aircraft?