Machine Learning and Artificial Intelligence are speeding up the development of new crop varieties to adapt to climate change — to sustain heat!

Climate Adaptation Summit 2021 took place on 25 January 2021 to accelerate the implementation of the 2015 Paris Agreement on Climate Change. The summit started, in the opening sessions, with the urgency to accelerate the implementation of the Paris Agreement. Economy is the Environment and Education (People). Time is limited to catch up and to keep the world under the 2 degrees Celsius, a pledge that was made five years ago.

Climate Change Adaptation Summit of 2021 — The opening of the summit, January 25, 2021

A new Science Declaration on Climate Change Adaptation has been also launched in conjunction with the summit, a lesson learned from the fight against Covid19. Science’s role is critical as it is helping now to fight this horrible pandemic and in the recovery transition. In the not so far past, science helped to successfully stop the ozone layer depletion, by implementing the 1987 Montreal Protocol to reduce the use of the man-made chlorofluorocarbons (CFCs). To quote:

“Science was helpful in showing the path, diplomats and countries and industry were incredibly able in charting a pathway out of these molecules (CFCs), and now we’ve actually seen the planet starting to get better. It’s a wonderful thing”, Susan Solomon & Jennifer Chu (MIT 2016).

Adaptation in agriculture — ML/AI to search for adaptive traits (non-modified genes) in crops to help speed up food production

One of the UN 17 Sustainable Development Goals (SDGs) is to achieve food security and improved nutrition within a sustainability perspective, by the year 2030. These new SDGs succeeding the previous UN Millennium Development Goals are all interconnected. Interestingly it is the food that connects them all as per the embedded model by the Stockholm Resilience Center.

Figure 1: This model with embedded SDGs was developed by the Stockholm Resilience Center (Azote Images for Stockholm Resilience Centre — 2017).

Changing climate conditions

As we are in the midst of changing climate change, there is an urgent need to speed up operational processes to produce more food to achieve food security and agriculture sustainability. As illustration of current changing climate conditions we have used climate datasets of Canada to examine the hypothesized trends or shifts in some of the climate variables, such as changing trends in temperatures.

Figure 2: Mean Temperature (°C) over time (on left stations and on right maps generated based on kriging techniques) for 4 different years (1995, 1975, 1995, and 2015) — Meteorological Data from Environment Canada

The figures above are illustrations of temperature trends, in Canada, for winter and summer of the year 1955, 1975, 1995 and 2015, respectively. These maps show that the changes are more noticeable during winter as monthly average temperatures of January continue to increase.

Figure 3: Record-Breaking Climate Trends Briefing — July 19, 2016 — Higher than normal temperatures are shown in red and lower then normal temperatures are shown in blue. Credit: NASA/GISS

The trend of the increase in temperatures is a global phenomena with the extreme north registering more abnormal increase. The map above produced by NASA, using Robinson projection, displays global surface temperature anomalies for the period January 2016 through June 2016.

ML/AI to speed up adaptation and mitigation

To adapt to changing climate conditions we searched for adaptive traits, using different machine learning techniques where the different layers of climate maps or surfaces, such those above were used as predictors, including different surface maps. In this process, different sources of climate surface data were used including large data sets from the Canadian Centre for Climate Modelling and Analysis.

Figure 4: Surfaces of temperatures used to search for traits in the samples — Illustration prepared by my friend Dag Endresen with whom and other colleagues from different countries we conducted this ML-based research.

The other dataset used in the modeling process included recorded data from large number of plant samples that are stored in genebanks, worldwide. The machine learning techniques were then performed to virtually evaluate whether these plant samples have the traits needed to provide crops with resilience to sustain climate change, such as tolerance to heat.

There are more than 7 million plant samples stored in more than 1 750 genebanks, worldwide. Such samples can be the source of traits that can have impressive impacts on plant crop yields, such as the traits found in the Japanese wheat “Norin 10” plant samples.

Figure 5: Major genbanks worldwide with safety deposits in the Svalbard Global Seed Vault (Norway). The radius of the circles is proportional to the number of samples deposited (Credit: PLOS ONE — Global Ex-Situ Crop Diversity Conservation and the Svalbard Global Seed Vault: Assessing the Current Status — Ola T. Westengen et al. 2013)

The samples that were virtually screened to likely have the traits of adaptation to sustain heat were grown in the field to confirm whether they actually have the traits as predicted by the different ML models.

Interestingly the agreements, based on AUC curve and other metrics, were found between the ML predictions and the actual real field evaluation and observations. Those sample plants that have been predicted and selected by the models to sustain heat virtually are also those that sustained heat under the real heat conditions. The plants predicted by the models to have heat traits, they also have the ability to lower their surface temperature , under heat conditions, when compared to a random sample of plants (figure below).

The plants identified as likely to have the sought for traits of adaptation are currently used in the development of several crops, worldwide. Some of the traits found have been searched for in vain, in the past.

Figure 6: This is the filed where we have conducted one of the experiments to screen for plant with traits while also carrying the virtual ML/AI screening. The plants screened for heat traits lower their surface temperature.

The results demonstrate in practice the potential of ML and on the overall the potential of AI in speeding up the adaptation to and mitigation to climate change.

References

Machine Learning Speeding Up the Development of Portfolio of New Crop Varieties to Adapt to and…

Bari, A.(2018) Machine Learning at Work: Speeding Data Discovery. ISBN-13: 978–1973573951 https://www.amazon.com/dp/1973573954

Bari, A., A.B. Damania, M. Mackay and S. Dayanandan (Eds.). 2016 Applied Mathematics and Omics to Assess Crop Genetic Resources for Climate Change Adaptive Traits. CRC Press, Taylor & Francis Group, Boca Raton, FL, USA. ISBN 9781498730136. . https://www.routledge.com/products/9781498730136

Bari, A., H. Khazaei, F.L. Stoddard, K. Street, M.J. Sillanpää, Y.P. Chaubey, S. Dayanandan, D.F. Endresen, E. De Pauw, A.B. Damania (2016). In silico evaluation of plant genetic resources to search for traits for adaptation to climate change. Climatic Change 134(4): 667–680. http://dx.doi.org/10.1007/s10584-015-1541-9

Some other links on ML/AI and “big data” in agriculture:

Mathematics helps find food crops’ climate-proof genes

The Water Warriors: 12 Hot Drought-Fighters in the Advanced Bio-economy

Big Data’s Big Role in Agriculture

In silico evaluation of plant genetic resources to search for traits for adaptation to climate change. Climatic Change 134(4): 667–680. http://dx.doi.org/10.1007/s10584-015-1541-9

Applied Mathematics and Omics to Assess Crop Genetic Resources for Climate Change Adaptive Traits