2018 & 2019 WinnerUsing commercial microwave links (CMLs) to estimate rainfalls
The Inspire Challenge is an initiative to challenge partners, universities, and others to use CGIAR data to create innovative pilot projects that will scale. We look for novel approaches that democratize data-driven insights to inform local, national, regional, and global policies and applications in agriculture and food security in real time; helping people–especially smallholder farmers and producers–to lead happier and healthier lives.
This proposal was selected as a 2018 pilot project and 2019 scale-up runner up project, with the team receiving a total of 225,000 USD to put their ideas into practice.
Using commercial microwave links (CMLs) to estimate rainfalls
Accurate, real-time rainfall measurements can be challenging to obtain in developing economies as traditional rainfall monitoring techniques (rain gauge, satellites, radars) can be costly and weather stations are often sparsely located. This data gap leads to high basis risks of rainfall-based index insurance, which hurts smallholder farmers.
However, in many regions where traditional rainfall data is unavailable, mobile phone service provider networks are widespread. The wireless commercial microwave links (CMLs) used in these networks are widely deployed, and, because rainfall causes attenuation to the radio signals between transmitter and receiver stations in the network, CMLs can be used to draw reliable rainfall estimates based on changed observed in the quality of the signal.
Working with data from several cellular network operators in various locations around the world, as well as data from household surveys, weather stations, and satellites, this project proposes to demonstrate the potential of using recent advances in CML technology to estimate rainfalls in crop production monitoring and help design better rainfall-based index insurance, ultimately benefiting farmers and poor households.
CMLs have the potential to provide quantitative rain estimates with high spatio-temporal resolution as measurements are taken typically every 15 minutes. Furthermore, the project offers a sustainable solution because the implementation cost is minimal; the network infrastructure is in place and the CML data is already collected and logged by many of the cellular operators for quality of assurance needs.
Additionally, many of these links are installed in areas where access is difficult such as orographic terrain and complex topography. Therefore, the CML method enables measurements in places that have been hard to access in the past or where rainfall has never been measured before.
This project is the first intended assessment of application of the CML technology in crop production monitoring and index insurance.
Step by step
Partnership for Kenyan data
The team partnered with the Department of Geo-Information Science and Earth Observation (ITC) at the University of Twente, Enschede, Netherlands.
The University of Twente provided CML and rain gauge data from Kericho, Kenya.
Acquisition of satellite data and comparison with rain gauge data
The team obtained satellite data from Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), an open source, 30+ year quasi-global rainfall dataset.
The satellite and weather station data have been compared with rain gauge data to show that CMLs can acquire reliable rainfall estimates which may, at times, even outpace that of conventional instruments which are sparsely deployed in the field.
Conference paper and presentation
The team authored a paper on the analysis of the CML and rain gauge data from Kericho that was accepted by the 16th International Conference on Environmental Science and Technology. The paper was presented at the Conference in Rhodes, Greece, 4-7 September 2019.
US$125K scale-up grant
The project was awarded a 2019 Inspire Challenge Scale-up grant of US$125K at the third annual convention of the CGIAR Platform for Big Data in Agriculture, 16-18 October 2019.
The team will submit a paper to Water.
Collaboration with insurance providers
Using existing insurance policies, the team will simulate the reduction of basis risks using CML rainfall information under different scenarios. These scenarios will then be compared to basis risks that use satellite and weather station rainfall.
The team hopes to set up a partnership with crop insurance providers in Guatemala.
Stay tuned for more!
This site features several initiatives that have already been launched.
Other initiatives the team is working on, that are in earlier stages of progress, will be reviewed once certain target outcomes are reached.
Project News and Resources
Meet all the Winners