A group of Cornell researchers has received a $1 million grant from the U.S. Agency for International Development to use machine learning to rapidly analyze agricultural and food market conditions, aiming to better predict poverty and undernutrition in some of the world's poorest regions. The method will use open-source, freely available satellite data to measure solar-induced chlorophyll fluorescence (SIF) – photons emitted from plants during the process of photosynthesis, detected by satellite, which can monitor agricultural productivity. It will also consider land-surface temperature, which provides information about crop stress under water deficit or excessive heat, as well as food-price data. "A method that can use near real-time, low-cost or freely available remotely sensed data can speed up the delivery of this information, and sharply reduce the cost," said Chris Barrett, the Stephen B. and Janice G. Ashley Professor of Applied Economics and Management in the Charles H. Dyson School of Applied Economics and Management, and the principal investigator on the three-year grant. "If you are a humanitarian organization trying to really target your resources at the poorest rural areas, this seems a powerful diagnostic tool."
Less than one-quarter of Earth's total cropland produces nearly three-quarters of the staple crops that feed the world's population – especially corn, wheat and rice, the most important cereal crops. These areas are our planet's major breadbaskets. Historically, when a crop failed in one of these breadbaskets, only nearby areas had to contend with shortages and rising prices. Drought-damaged corn on an Ohio farm, 2012.In 2012 heat and drought in the United States slashed national corn, soybean and other crop yields by up to 27 percent Famines are extreme events in which large populations lack adequate access to food, leading to malnutrition and death. Most of these deaths are caused by infectious diseases than starvation because severe malnutrition compromised immune systems.
In the Amhara region of Ethiopia, farmers have given up on one of their staple crops. "Once our village was a major producer of faba bean," says farmer Yeshewalul Tilaye, from the Chichet village of Tarma Ber, "but we lost hope." Disease and natural resource degradation have plagued the Amhara region, which has a 90 percent poverty rate and is particularly susceptible to both drought and heavy rainfall. Before the Ethiopian civil war broke out in the 1970s, pulses - the family to which faba beans belong - were the nation's second biggest export crop. Since then, production has decreased dramatically, partly due to recurrent droughts, prevailing diseases and a lack of investment in research to address these production constraints.
India is in the grip of a severe drought as a result of two successive weak monsoons and a searing heatwave. Its reservoirs dipped to less than a fifth of their total capacity in May, and a quarter of the country's 1.1 billion people are estimated to be affected in some way. Reports of parched, cracked soils, farmers' suicides and desperate migration from Marathwada in the west of the country – one of the worst-hit regions – are at odds with the country's image as an emerging economic and technological power, aspiring towards a trillion-dollar economy "with no poverty" by 2032. The hope is that this year's monsoon, due to arrive in the first week of June, will turn things around. But many see the drought as a wake-up call for India, and a sign of things to come for the region as global warming takes hold.
Satellites are great for communication, weather forecasting, and a number of other activities. Now there's one application we haven't previously come across -- building up heat maps of the world's tropical forests. When combined with some neat statistical tools, they can predict regions that might be in trouble. It was recently described in a paper for the journal Nature Climate Change, entitled "Remotely sensed resilience of tropical forests." "We've got large amounts of satellites monitoring these forests, and we discovered that we were able to use time series information from them to look at the dynamics and resilience of the forest," lead author Professor Jan Verbesselt told Digital Trends.