Summer in Estonia is about to end and our team is getting more and more busy. These are the latest news from our team.
1. Important in August
Vacations are mainly over, and August has been a busy month in and around KappaZeta.
Firstly, I’m glad to welcome Tanel Kobrusepp to our team as the product manager of crop insurance oriented services from 1st of August. Tanel has important mission to lead our business and product development in the growing agri-insurance services market. KappaZeta has been traditionally strong in science and engineering and not so on the business side. With Tanel Kobrusepp joining this is about to improve. Coming months will tell. I wish Tanel a lot of courage to take the leadership, make clients happy and things happen.
While making deals and developing the business, it is equally important to be deep and have content. In August two important PhD thesis were defended in the University of Tartu. On 23rd of August KappaZeta’s friend and an unofficial team member Tauri Tampuu defended his PhD thesis “Synthetic Aperture Radar Interferometry as a tool for monitoring the dynamics of peatland”. After mine, Karlis Zalite’s, Aire Olesk’s and Tanel Tamm’s doctoral thesis this was the 5th doctoral thesis in the University of Tartu on synthetic aperture radar data. Welcome to the club, Tauri!
On 25th of August KappaZeta’s software developer Heido Trofimov defended his PhD thesis “Polluted clouds at air pollution hot spots help to better understand anthropogenic impacts on Earth’s climate”. An important piece from the critical puzzle to understand how we humans alter the climate on Earth. Heido is now the 5th member in KappaZeta team with doctor’s degree. Congratulations!
It has also been busy days with improving KappaMask, our free and open cloud mask for Sentinel-2, even if the results are not yet so visible. By August more than 5000 Sentinel-2 sub-tiles have been carefully manually labelled to give our AI model a high-quality global reference set, which is a pre-requisite for a globally accurate cloud mask – your AI model is just as good as your reference data.
Great job, our interns Abdullah, Catherine, Joosep, Mariana and Nikita for doing the hard work and Olga & Tanya for managing the development and improving the model. I’m sure the results will be satisfying once we measure the accuracy and KappaMask will be an important tool for the world in taking full advantage of Sentinel-2 data.
Kaupo Voormansik, CEO of KappaZeta
2. Crop insurance oriented servicesPeople and companies insure everything from cars, homes to travel expenses. Crop insurance does not seem to be as popular, at least in the European countries. For example, only 10.8% of farmers insured their fields in Poland, even though insurance was made compulsory in 2008 to receive full aid in case of a loss. Otherwise, the payment is reduced by 50%.
On the other hand, ~87% of crop fields in the U.S. are insured, with more than 1.1 million policies issued in 2021.
There are a lot of blockers on both, the producers and insurance side, that are causing the underuse of crop insurance. The main blockers for producers to insure their fields are price, lack of flexibility for custom terms from the insurance companies and lack of insurance products to choose from.
New technologies and data need to be incorporated into insurance companies’ work to increase the amount of tailor-made insurance policies in a cost-effective manner, thus increasing the interest in crop insurance products.
One option is to use Earth Observation (EO) data, which has endless opportunities from faster underwriting and better risk assessment to reducing costs on time-consuming and expensive claims handling. Imagine a loss adjuster going to a 3m high maize field, where a loss has occurred. Using satellite data, the loss adjuster can automatically see on a portable device, where exactly the damages happened, so he/she does not have to spend hours looking for the damaged areas. It is also very difficult to assess the extent of the damage with bare eyes, but it can definitely be done by AI, which could automatically determine how many acres were damaged, using satellite imagery.
Our main goal right now is to determine the biggest problems that the agricultural insurance providers face and prioritize our development of solutions according to their needs.
I am very excited to be working on these solutions with my amazing team of AI, Machine Learning and Earth Observation specialists. If this is a topic that you feel related to, don’t hesitate to get in touch with me at tanel.kobrusepp@kappazeta.ee.
Tanel Kobrusepp, product manager of crop insurance oriented services
