It’s been a tumultuous year for Planet Earth with heatwaves, droughts, floods, and forest fires dominating headlines. Extreme weather-related events have increasingly become the norm and a landmark UN report out last week paints a stark picture of the risks associated with rising temperatures across the globe.

It’s clear we live in volatile times, and as food crops are particularly sensitive to variations in growing conditions, our increasingly erratic weather is hitting soft commodities and their supply chains hard.  A poor potato crop this year in Europe, for example, led to strained retail relationships and caused havoc for factory planners and buyers. While there were ominous signs during the season, it was difficult to forecast precisely what the yields would be until the harvest season began. As a result, planning was both painful and stressful for all concerned.

Meanwhile, in the longer term, the rising frequency of extreme weather events means farmers will need to adapt their operations to ensure their land remains productive (for example through irrigation or drought resistant seeds) – important decisions that will demand considerable thought and investment.

However, there is good news. Advances in machine learning are enabling us to help those producing food and managing our food supply make better climate-smart decisions for the future, and regenerate Earth’s natural capital in the process.

Cervest’s next-generation software has been developed by some of the world’s leading scientists and AI experts. Our pioneering platform combines statistical science, computational sustainability, and agronomy with data from multiple sources – climatic, scientific, satellite, biophysical – and decodes it into genuinely useful and actionable intelligence.

We can deliver field-level personalised yield predictions anywhere in the world, earlier in the season than ever before without expensive on-farm equipment. And by tracking and predicting crop productivity, growers and buyers are able to plan earlier, saving scarce natural and financial resources.

Beyond watching the current season unfold in real time, our platform’s machine learning capabilities have also supercharged our ability to predict what will happen next, by continuously learning from billions of data points, across multiple crops and time periods.

Using these to simulate agricultural scenarios into the future for the first time, our approach also enables us to recommend more climate-smart farming practices. From new planting techniques to alternative seed types or crops, scenario modelling can help growers understand how to adapt for future productivity, and create a more resilient food supply ecosystem for everyone.

Leading companies, such as Mars are already embracing more sustainable ways of buying, committing $1bn to further support its growers and the land from which they source – technology has the power to enhance this even further.

Beyond industry, policy makers and NGOs can use AI to arm themselves with early predictions to help the world’s 570 million farms around the world adapt to climate change.

Artificial intelligence is enabling us to learn from nature, in order to protect it. And by doing so, we believe humans and machines together are now able to solve some of the world’s most complex food, agriculture and supply chain challenges – securing food supplies and sustaining the planet for future generations where volatility is the new normal.

This article originally appeared on techUK.org on 15th October as part of Green Week. See #techUKGreenweek for more content.

Photography is by Hal Gatewood on Unsplash.

Ernesta Baniulyte 
Product Designer

Ernesta has been a full-stack product designer for more than five years. She has valuable experience in the B2B, B2C and B2B2C worlds, and while working at both agencies and product/service companies, she has learned to develop UX research infrastructures to support strategy.

At Cervest, Ernesta contributes to all stages of the product development process – from initial ideation to the exacting detail of UI design – finding new ways to visualise data, and ensure our product is intuitive and user friendly.

Ernesta’s decision to join Cervest was inspired by her desire to make the world a safer, better and more aware place.

Ramani Lachyan 
Junior Research Scientist

Ramani joined Cervest after obtaining her Master’s in Physics from ETH, Zurich. She brings with her valuable experience gained through working on model building and data simulation pertaining to neutrino physics.

Ramani has joined Cervest as a Junior Research Scientist and will be working on creating algorithms that allow for the extraction of physical observables from data from a range of sources.

.

Lukas Scholtes 
Statistical Scientist

Lukas completed his maths BSc at ETH Zurich, followed by an MSc in statistics at Imperial College. He wrote his MSc thesis in collaboration with Cervest, on the modelling of North American wheat yields via Bayesian parametric and non-parametric methods.

Following an internship in the NGO sector in Bangladesh and a stint in the world of fintech, Lukas comes to Cervest, excited to apply himself to the challenges that are arising as a consequence of unsustainable land-use policies and climate change.

Aidan Coyne
Junior Researcher

Aidan is currently pursuing a Bachelor of Arts and Sciences in Science and Engineering at University College London with a focus on computer science and data informatics.

At Cervest, Aidan is working on researching and assimilating a database of articles categorising the reasons for extreme decreases in crop yields across Europe. The information will be used to help predict the impact of weather events on crop yield and contribute to  Cervest’s ability to bring clarity to decision making around climatic and extreme events.

While studying, she also volunteers with environmental conservation groups and youth engagement programmes.

Jasmine Thompson
Engineering Resident

Jasmine’s background is primarily in Python programming with a focus on data analysis and visualisation.

Since graduating, she has worked on data insights for a London-based dating app startup, helping the company understand the user base and guide new growth. She is now excited to use her skills to help Cervest deliver playback data and useful data analysis and is passionate about the potential of data science, machine learning and visualisation tools.

While studying at Westcliff High School for Girls she was involved in a variety of projects including GUI design for BAE Systems and data collection for a surveillance vehicle project sponsored by Leonardo S.p.A. She was also the Data Analyst for a long-running Southend Youth Council project that advocated for students having better mental health services in school.

Stoyan Binev
Junior Software Engineer

Stoyan is a BSc student at King’s College London with two years’ experience in software engineering.

With experience working for Amazon and Google as a software engineer, as well as for a fintech start-up, Stoyan was inspired to join Cervest’s by its planet-wide scale and the opportunity to make a positive impact in the world.

He is currently finishing his degree and dissertation while also specialising in data processing at Cervest.

Agnes Schim van der Loeff
Policy Researcher

Agnes joined Cervest after completing her BA in Arabic and Development Studies from SOAS University of London. She is interested in the intersection of the social, economic and political dimensions of climate change and passionate about climate justice. During her studies she was also engaged in environmental activism, including as environment officer in the SOAS students’ union.

Agnes started at Cervest as a research resident exploring the ethical implications of AI in relation to climate change, which resulted in a paper selected for an oral presentation at the NeurIPS 2019 workshop on AI for social good. Building on this, she is developing an ethical framework for Cervest. As policy researcher she now does research on the regulatory context of Cervest’s work and on emerging policies relating to climate change. 

Kate Chkhaidze
Machine Learning Scientist

Kate joined Cervest after completing her PhD study at the Institute of Cancer Research, University of London. Her Project was on statistical and computational modelling of cancer evolution. Her educational background is in pure mathematics (BSc – Tbilisi State University) and statistics (MSc – Imperial College London). Before deciding to study for a PhD, she worked as a junior analyst/developer at the Bank of Georgia and in parallel was giving lectures in Statistics to undergraduate students in Tbilisi for almost two years.

At Cervest, she will be working as a Machine Learning Scientist on crop classification problems. She loves the mission and goal of the company and is very excited to be a part of the process of achieving it.