Varun’s second chapter of his dissertation has been published

PhD Candidate Varun Tiwari’s second PhD paper has been published in PLOS ONE journal.

The study focused on improving the boro rice yield estimation to help with food security and agricultural planning. The study focused on Bangladesh, which is the world’s third-largest producer of rice. The country is also the sixth most-vulnerable country in the world to climate change, as the destruction of rice crops by flooding has led to food insecurity.

Accurately quantifying boro rice yields is important to plan for and mitigate climate impacts on rice production, and can supplement traditional methods such as field surveys.

Researchers used a series of images of the same location recorded at regular intervals – known as time series satellite imagery – to measure vegetation and growth conditions, crop water content and soil condition at those locations. By combining that satellite data with field data, researchers trained their machine learning model to more precisely estimate rice crop productivity for the period from 2002 to 2021.Accuracy has ranged between 90-92 percent with around 2 percent uncertainty, which refers to the model’s margin of error.

The analysis found that 23% of the rice-growing areas are seeing increasing yields in boro rice, while most areas (76.5%) have stable yields, and only a small fraction (0.11%) are decreasing.

This is the first comprehensive attempt to estimate boro rice yields at this scale, and it offers valuable insights that could inform policy to increase food security in Bangladesh. Satellite imagery from sources like MODIS can be leveraged in combination with machine learning algorithms to estimate crop yields as shown in this example. Additionally, the approach could be adapted for use in other regions around the world.

Read the full article here.

Social Media Buzz: