What is it about?

Climate change has poorly impacted the world in many ways. For example, in countries that grow their own farming produce, climate change hinders the growth of high-quality crops. In Vietnam, a region known as Binh Thuan experiences a very dry climate. It even leads to heavy sandstorms, severe water shortage, and desert-like conditions. As a result, crops don’t survive easily in this region. The authors of a study wanted to look at the environmental changes occurring in specific regions of Vietnam. By doing this, they wanted to provide local farmers with the information needed to adapt to these changes. At present, the “weather station model” provides information on the temperature, wind speed, and cloud cover in a region. Sadly, this model has low accuracy since the impact of climate change varies with each region. Keeping these gaps in mind, the authors combined a machine learning (ML) and wireless sensor network (WSN) to create an advanced WSN technology. This technology comprised three parts. The first part collected data on sand movement via sensors. The second part added the data to an online platform, which is available to farmers or the local government. The third part made use of ML to predict weight and volume of sand. This technology could monitor dynamic and rapid changes, even in complicated environments. In addition, it picked up and processed new environmental information easily. Upon testing in Binh Thuan, this technology could predict sand movement in an effective and affordable manner.

Featured Image

Why is it important?

The newly developed technology can improve the growth of crops and the quality of life of people in Vietnam. It can also help cut down costs linked to farming losses. By accessing the information provided by this technology, local people, farmers, and the government can join forces to tackle the effects of climate change. KEY TAKEAWAY: A new ML based method can predict environmental changes in Vietnam. It is an affordable and accurate alternative to traditional methods and provides dynamic information on sand movement in the country.

Read the Original

This page is a summary of: Wireless sensor networks and machine learning meet climate change prediction, International Journal of Communication Systems, November 2020, Wiley, DOI: 10.1002/dac.4687.
You can read the full text:




The following have contributed to this page