Effigis and CRIM Working Together to Save our Soil

Nitrogen fertilizer: The Farmer’s Worst Enemy

Since the 80’s, farmers have been making intensive use of nitrogen fertilizer, which has a negative effect both on the environment and human health. According to the UN Environment Program 2020 Study, nitrogen is both “too heavily used in some places – leading to environmental disasters – and poorly distributed in others – leaving the poorest regions in dire need.”

Over the years, this practice has expanded globally and new challenges are emerging:

  • When applied outside the optimal period, fertilizer can end up in streams and rivers, causing a proliferation of algae (eutrophication) in these waterways.
  • When the amount of fertilizer is applied without knowledge of soil properties or plant needs, some may remain in the soil that is not completely absorbed by plant.
  • To estimate the required nitrogen needs, farmers rely on recommendations that are not necessarily based on adequate geospatial information. This unreliable model opens to the door to bias.
  • Measurements based on field surveys do not provide an overall view of geographic areas and soil textures at time of fertilization.

The Solution: Satellite Imagery and CRIM Machine Learning

Precision agriculture helps the farmer make better decisions. It is based on technological tools that allow, among other things, to map soils and help determine the optimal amount of fertilizer according to spatial variability of soil and other characteristics such as humidity, crop vigor, etc.

One of these tools, satellite imagery, spearheaded precision agriculture. In Québec, Effigis Geo-Solutions has developed a nitrogen fertilization recommendation tool for corn fields, based on research conducted by Agriculture and Agri-Food Canada. This tool is based, among other things, on soil texture inferred from the analysis of a time series of satellite measurements.

Effigis called on CRIM to help it exploit the data within these series of satellite images using machine learning techniques. The goal: to retrieve information on soil texture at a more detailed scale than that of 1/20000 soil maps, through high spatial resolution satellite images. And since fields are not created equal (i.e. different topographies, drainages, textures), nitrogen should be prescribed at variable rates.

As a result, the corn field nitrogen recommendation tool now provides more detailed soil information than ever before. As a result, nitrogen maps gain in precision.

Improved precision, improved fertilizer use, improved productivity 

A farmer who traditionally applied 170 kg of nitrogen fertilizer per hectare can now adjust the amount of fertilizer by considering the most important parameters, as prescribed by the Effigis model. The result is better crop yield, consistent with sustainable development principles.  Agronomic consulting firms using the Effigis model are very satisfied with the results.

CLIMATEDATA.CA applied to transportation

November 1, 2021

Glasses-Free 3D Screen. Did you say glasses-free?

October 5, 2021

CLIMATEDATA.CA applied to Buildings

September 15, 2021

CRIM researcher receives a Discovery Grant

July 5, 2021

CLIMATEDATA.CA applied to agriculture

June 30, 2021

CLIMATEDATA.CA applied to healthcare

June 23, 2021

CRIM is part of an initiative to accelerate talent integration in businesses

April 15, 2021

The growing threat of deepfake

April 13, 2021

The chatbot: the survey’s best friend?

March 10, 2021

Emotions and Stress Detection in drone Operators

February 12, 2021

Social Media: a new book tackles privacy, security and disinformation issues head-on

February 9, 2021

Jakarto keeps a tally of fire hydrants in your city

February 1, 2021

UEAT and CRIM: A Win-Win Collaboration

November 24, 2020

VITAC acquires SOVO Technologies, a CRIM spin-off company

October 14, 2020

CRIM and K2 Geospatial, two Québec organizations with over 25 years experience, talk about adapting to climate change

October 5, 2020

The evolution of planet Earth is everyone’s business

September 11, 2020

Applying CRIM’s speech technology to Indigenous languages

December 5, 2018