top of page
Black Soil

Soil Quality Evaluation System


With constant growth of the earth’s population humanity faces the problem of secure and sustainable food supply. Especially developing countries are often hit by famine and have not enough affordable and nutritious food to feed all people in need.

Presently, nearly 10% of the world’s population suffers from severe food insecurity [1]. But this situation will become even worse: according to UN, the earth’s population is expected to reach 9.7 billion by the year 2050 [2], which will result in a food demand 69% higher (measured in calories) than in 2006 [3]. Thus, we currently face an extremely urgent and complex challenge of creating sustainable and scalable food supply chains, especially in developing world.

One of the key components to master this challenge is to increase the crop yield [4]. To do so, it is an imperative to have detailed knowledge about the properties of the soil used for farming. Having this information, it is possible to make better decisions regarding fertilization efforts and choice of the crop to be planted (crop rotation). Additionally, soil characteristics can be used to optimize pesticide use which can be an eco-friendly action. These are important for farmers of any size and location but especially for small farmers in developing regions where survival depends directly on their yield and on their soil.

Chemical lab tests broadly used in developed regions to measure the quality of soil are often inaccessible for farmers in developing countries due to high costs and lack of expertise. Thus, knowledge about properties of the used soil remains inaccessible to many farmers. MI4Peole aims to contribute to the solution of this challenge using Machine Intelligence (MI).


Creation of a free of charge MI system that can predict most important quality indicators for soil without performing expensive chemical lab tests and can be directly used by farmers of any educational level. The system should be able make these predictions based on various data inputs, like satellite imagery, infra-red spectral measurements data, etc., and will be able to improve its predictions whenever it is able to cross-validate its predictions with chemical test data.

Expected Impact

This system will enable farmers in developing countries to better understand their soil, make intelligent choice about which crops to plant, and to fertilize and protect soil from pests in a more suitable, sustainable, and environmental-friendly manner. It will lead to better crop yields with eco-friendly farming and, as consequences, to more stable food supply chains, less famine and undernutrition.

Project Phases

  • Phase 1: Research and Proof-of-Concept
    This phase is dedicated to researching on how various data inputs can be used to predict soil quality using MI. It serves as proof of feasibility for the planned Soil Quality Evaluation System and provides the scientific foundation for the whole project.

  • Phase 2: Building Application
    This phase is focused on building a working prototype of the Soil Quality Evaluation System.

  • Phase 3: Field Study
    Using the results from Phase 2, a field study will be performed that measures the actual impact of MI-based soil quality evaluation system on the crop yield of farmers in developing countries.

  • Phase 4: Release to Community
    If Phase 3 will show positive and impactful results, MI4People will make relevant software code, MI-models/tools and any other intellectual property created during the project publicly available and will create a community of enthusiasts who will proceed to maintain and improve the application as an open-source project.

Current Status


Phase 1 is running.

Opportunities for Contribution


We are currently searching for Data Engineers, Data Scientists, and Agricultural Experts who would be ready to contribute to the project as volunteers.

We also would be very grateful for any donations in cash or kind to support this initiative.

bottom of page