In the new GSMA AgriTech report, Mobile Technology for Climate Resilience: The role of mobile operators in bridging the data gap, we explore how mobile network operators (MNOs) can play a bigger role in developing and delivering services to strengthen the climate resilience of smallholder farmers. By harnessing their own assets and data, MNOs can improve a broad suite of weather products that are especially relevant for farming communities. These include a variety of weather forecasts (daily, weekly, sub-seasonal and seasonal) and nowcasts, as real-time monitoring and one- to two-hour predictions are often used for Early Warning Systems (EWS) to prevent weather-related disasters. MNOs can also help strengthen the value proposition of other climate products, such as weather index insurance and decision agriculture.
Why do we need more weather data?
Agriculture is highly dependent on regional climates, especially in developing countries where farming is largely rain-fed. Smallholder farmers, who are responsible for the bulk of agricultural production in developing countries, are particularly vulnerable to changing weather patterns – especially given their reliance on natural resources and exclusion from social protection schemes. However, the use of climate adaptation approaches, such as localised weather forecasts and weather index insurance, can enhance smallholder farmers’ ability to withstand the risks posed by climate change and maintain agricultural productivity.
Ground-level measurements are an essential component of climate resilience products; the creation of weather forecasts and nowcasts starts with the analysis of ground, spatial and aerial observations. This involves the use of algorithms, weather models and current and historical observational weather data. Observational instruments, such as radar, weather stations and satellites, are necessary in measuring ground-level weather. However, National Hydrological and Meteorological Services (NHMSs) in developing countries often lack the capacity to generate accurate ground-level measurements beyond a few areas, resulting in gaps in local weather data.
While satellite offers better quality resolution than before, and is more affordable and available to NHMSs, there is a need to complement this data with ground-level measurements. This is especially true in tropical and sub-tropical regions where most smallholder farmers live, where variable local weather patterns can lead to skewed averages from satellite data.
What data do MNOs have to enhance the climate resilience of rural communities?
While the rising use of mobile has seen the emergence of value added services such as weather forecasts via SMS, the growth of mobile connectivity in rural areas is also creating more opportunities to use MNO assets to generate valuable data for climate resilience products.
A growing number and variety of sensors are available to monitor environmental variables, opening up new possibilities for Internet-of-Things (IoT)-based weather products. For example, under the UNDP CIRDA initiative, MNOs in Sub-Saharan Africa have co-located IoT-enabled automated weather stations (AWSs) with their base stations to enhance the capacity of NHMSs. The use of Call Detail Records (CDR) has also shown potential to track population movement because of climate-related crises. In Colombia, Telefonica and FAO use CDRs and other data to enable the government to implement social protection measures and reduce climate-related displacement. In addition, the use of user location data can support the creation of relevant, contextual services, from farm-level weather forecasts to accurate weather and crop insurance.
What is virtual sensing?
Virtual sensing, also known as passive or opportunistic sensing, is the idea of using a range of connected objects for environmental monitoring and as a source of weather data. These include smartphones, connected cars and commercial microwave links (CMLs) used in mobile networks to transmit signals between base stations.
CMLs are ground-level radio connections used in mobile telecommunication networks globally. During rainfall, these microwave signals are attenuated – leading to changes in the signal strength between transmitting and receiving base stations. Using an algorithm, CML data can be analysed and converted into realistic and accurate rainfall measurements, effectively turning a mobile network into a virtual network of rain gauges.
In 2019, the GSMA’s AgriTech Programme, with supported from the UK’s Department for International Development, began a collaborative partnership with Wageningen University & Research and the Royal Netherlands Meteorological Institute (KNMI) to improve rainfall monitoring services for agriculture and weather warnings in developing countries. The initiative involved the implementation of a proof of concept on CML for rainfall retrieval in Bangladesh, Nigeria and Sri Lanka.
Assessments based on the results of the pilots showed that CML data is a viable and realistic source of detecting rainfall in tropical environments. CMLs can provide granular detail on the spatial and temporal evolution of rain showers, making them a prominent virtual sensing data source. The results of the pilots showed that it is possible to use CMLs as an alternative or complementary source of rainfall monitoring in developing countries. Merging CML-based rainfall estimates with satellite data and rain gauge readings could produce a much more complete ground-level picture.
Comparison between satellite data (GPM IMERG) and CML data during a daily rainfall event in Sri Lanka
While CML data is readily available globally, there are some challenges in using the data for climate resilience products – both in terms of the operational model used to extract and compute the data and the overarching business model. For example, from a technical standpoint, the algorithms required to interpret and map CML data must be optimised for the specific weather parameters of each region. In the GSMA-led pilot, the use of the RAINLINK algorithm based on the weather parameters of the Netherlands led to overestimated rainfall measurements in some cases.
What is the opportunity for MNOs with CML data?
With the necessary infrastructure already in place, MNOs have an opportunity to improve the quality of climate resilience products for smallholder farmers and, more broadly, to communities affected by weather and climate-related challenges. For instance, MNOs could collaborate with commercial weather companies or with insurance providers interested in CML data for rainfall retrieval. MNOs could also foster public-private partnerships with local NHMSs to augment local weather monitoring and forecasting. Most NHMSs in developing countries lack sufficient ground-based measurement equipment and would benefit from low-cost solutions that enhance their ability to carry out specialised analysis.
However, to enable the use of CML data commercially, MNOs will need to establish viable business models to support these partnerships. To date, MNOs have provided their CML data for pilots and tests at no cost. Such open data initiatives are crucial to improve and develop climate resilience products and to support governments and NHMSs – particularly in developing countries. As the value of this data becomes apparent, MNOs will have an opportunity to monetise the use of their CML data. How CML is ultimately used will depend on the nature of partnerships between MNOs, third-party data processors and customers of the processed data.
In our new report, you will find further detailed analysis on the use of CMLs and other mobile data to support climate resilience services for smallholder farmers. We welcome your feedback and comments.