Alexander Menshchikov, Head of the Artificial Intelligence for Autonomous Systems Laboratory at the Skoltech AI Center, participated in the round table discussion “Big Data and Artificial Intelligence in Crop Production: Present and Future” held at Crocus Expo as part of the annual AgroTech Expo 2025.

The agricultural industry remains one of the most conservative sectors when it comes to implementing innovations. Digitalization in agriculture is still at an early stage, and farmers often face barriers to adopting technologies due to mistrust and concerns about their effectiveness. However, artificial intelligence is already capable of solving key industry challenges, including assessing soil and plant conditions, monitoring planting and harvesting processes, predicting yields and adverse weather events, and optimizing conditions for crop growth.

Projects from the Skoltech AI Center:

Alexander Menshchikov shared the developments from his laboratory, which are being carried out in collaboration with the “Multimodal Data Processing” group led by Dmitry Shadrin. These developments aim to apply AI technologies and autonomous systems in agriculture. Four key case studies were presented:

1. Seed Germination Monitoring
   A machine vision system for automatically analyzing seed germination, providing 24/7 monitoring and eliminating human error. It assesses germination speed, environmental conditions, and optimizes environmental parameters to improve seed quality.

2. Biomass Growth Prediction
   A system based on CNN and LSTM neural networks predicts leaf growth in greenhouse tomatoes, helping control plant biomass, improving yield management accuracy, and optimizing greenhouse resource use.

3. Leaf Area and Biomass Assessment
   A machine vision system used in an experiment on a 720 m² plot employs convolutional neural networks to create segmentation masks, accurately calculates leaf area and biomass at different growth stages, and provides data to enhance growing technologies.

4. Weed Detection Using Drones
   A real-time system effectively identifies and marks weed areas in high-resolution images, speeding up large-area analysis and simplifying field work planning.

“Artificial intelligence and autonomous systems have the potential to radically change the agricultural industry,” - Alexander believes, “For example, machine vision systems not only automate processes but also significantly improve the accuracy of plant condition analysis, yield prediction, and optimization of growing conditions. However, to make these solutions widespread, we must overcome mistrust and implementation barriers that still exist in the sector. Our task is to prove to farmers that AI is a reliable tool that can increase their efficiency and reduce costs.”

The event was organized by Agros Expo Group, with Evgeny Gribov, Head of Technology Development at the National Technology Initiative Platform (NTI Foundation), serving as the moderator.