Research Uncovers AI Tool For Predicting Agricultural Yields

0 354

An Artificial Intelligence tool has been discovered to help mitigate the harms of climate change and other crises in the agriculture sector.


The AI tool combines the use of satellite remote sensing and machine learning to predict agricultural yield of crops in Africa.


Pan-African research organisation AKADEMIYA2063 says the Africa Agriculture Watch (AAgWa) tool will aid the production of staple foods including, maize, cassava and sorghum, across 47 African countries.

The web-based platform, launched on 27 April, was designed to help tackle some of the impacts of climate change, conflicts and pests on food production.
Racine Ly, director for data management, digital products, and technology at AKADEMIYA2063, says Africa’s agricultural sector faces multiple threats, including supply chain disruptions, as a result of extreme climate events and health crises.

Relying on conventional analytic techniques alone will not deliver the effective decision-making we need to meet these challenges,” he stated.
The developers said AAgWa would give policy-makers timely access to high-quality, predictive analytics, which are often lacking on the continent.

The crops were selected largely because of their contribution to food security in Africa, as well as high trade value.

Our rural communities will, for example, consume more millet, sorghum, and yam,” he explained.

Those are not really used in international trade, but they are very critical in our livelihoods, so we rather focus on those because if they suffer from destruction or disruption these communities will also suffer in their livelihoods.”

The tool, developed by an all African expert team, took about two years to develop and involve intensive scientific review and satellite data collection.

He said there was need to ensure that the data was correct since it was the data that researchers and decision-makers would use to make decisions.


NP/Lateefah Ibrahim

Leave A Reply

Your email address will not be published.