NAX AGTECH has identified a critical need in the sector.
agricultural: the ability to accurately predict and manage the production of
crops in a world increasingly affected by climate change.
This project is focused on the development of an advanced prediction system for the
agricultural, taking advantage of satellite imagery technology and
machine learning. This innovative approach will enable farmers to
anticipate various factors that affect their land, such as soil moisture,
the presence of pests and diseases, and the impact of natural phenomena.
adverse weather. By providing a forecasting tool
accurate and reliable, NAX AGTECH seeks to transform the way we do business.
manage agricultural operations, promoting efficiency and sustainability
sector.

OBJECTIVES AND RESULTS:

In order to achieve this ambitious goal, the project is structured around
several specific objectives that ensure methodological development
rigorous:
● SO1: Develop accurate crop production forecasting models.
using satellite imagery data and advanced learning techniques
automatic.

● SO2: Implement automated sorting algorithms that enable.
predict the production of various types of crops on a large scale.
● SO3: Evaluate the accuracy and effectiveness of the developed prediction system.
through extensive testing in different agricultural scenarios.
● SO4: Analyze and adapt the system to effectively predict production.
under adverse conditions, such as droughts, floods and drought.
other climatic disturbances.
● OE5: Implement and test the prediction system in real cases of.
customers, providing practical validation of its usefulness and effectiveness.

Taken together, these efforts will enable farmers to make decisions
to optimize their operations and ensure a sustainable use of natural resources.
agricultural resources.

RESULTS 2024

NAX AGTECH, S.L. has initiated and advanced in this period of 2024 the
Crop Modeling for the Optimization of Agricultural Processes" project.
within the Framework of Sustainable Agriculture through the Use of Imagery
Satellites and Machine Learning", focusing its efforts on different
two main packages: management and dissemination, with the most important ones being
and the study of the state of the art. Regarding the management of the
and specific objectives have been defined, and the project has been
developed a detailed schedule for each work package. The team
weekly meetings have been held to review progress and adjust
strategies as needed.
In the second work package, related to the study of the status of the
and analyzed scientific and industrial publications have been compiled and analyzed.
prioritizing advanced techniques such as GANs, hybrid models
RF+DNN and hyperspectral technologies. Challenges have been identified and
opportunities, such as the correlation of spectral indices with performance
and arid land regions, and the potential of learning to grow crops in cloud regions and arid lands.
for hybrid models.