Agtech: A Pivotal Force Driving Climate Change Action in Agriculture
The agricultural sector is a significant contributor to global greenhouse gas emissions, responsible for an estimated 19-29% of these emissions according to the World Bank. This figure climbs even higher to 40% when we consider the emissions produced throughout the entire agricultural value chain, encompassing transportation, storage, and processing.
With the global population expected to double by 2050 and consequently increase demand for food, emissions from agriculture are expected to increase unless action is taken to stem the harm to the environment.
The solution lies in embracing agricultural technology (Agtech) to revolutionise agricultural practices, boost yields, increase farmer incomes, and promote sustainability. Technologies such as climate-smart agriculture, precision farming, soil carbon sequestration, and digital tools for value chain optimisation all aim at raising the production per square inch of agricultural land while recovering more from loss and damage.
Agtech offers numerous tools and techniques for sustainable crop and livestock management, including the use of climate-resilient seeds, and improved breeding techniques that result in higher yields with reduced land, water, and chemical inputs. By increasing the productivity of land, agtech helps preserve natural ecosystems, reduces deforestation, and prevents the conversion of additional land for agriculture, thus mitigating greenhouse gas emissions.
Soil health technologies are also important for transforming the output of agricultural land for increased food production and soil sequestration. Soil mapping and monitoring enable farmers to apply the appropriate nutrients in the right quantities leading to enhanced crop productivity and increasing the capacity to sequester carbon from the atmosphere. Additionally, through regenerative agricultural practices like cover cropping, reduced tillage, and agroforestry, agtech actively contributes to carbon sequestration.
As well, more climate goals are linked to climate-smart agriculture, which leverages digital technologies for weather forecasting and data-driven analytics to provide farmers with real-time information on rain patterns, crop diseases, and market conditions. As a result, farmers are equipped to make climate-smart decisions, such as adjusting planting schedules, selecting suitable crop varieties, and adopting climate-resilient farming techniques. The AgriBot co-developed by AGRA and Microsoft is one such agtech, designed to optimise resource utilisation and minimise climate-related risks, ultimately helping farmers adapt to changing climatic conditions. The AgriBot provides valuable agricultural information to farmers through SMS and social media platforms like WhatsApp and Telegram. Deployed in two Kenyan counties since 2020, the Bot today serves 47,470 farmers with vital information on good agronomic practices, pest management, weather prediction, and insurance as well as linkages to county approved agrodealers and certified seed varieties. The same is being scaled to three other counties in Kenya and three countries of Nigeria, Malawi and Uganda through the partnership of AGRA and IFC.
Precision farming involves the application of data collected using drones and sensors to drive precision irrigation and nutrient management. This minimises wastage of resources, prevents pollution from excess chemicals, and decreases the overall carbon footprint of agricultural operations. CropIn’s Smartfarm is a good example of farm monitoring and management solutions that utilise advanced analytics to help farmers geotag their land, digitise their records, and optimise their use of water, fertilisers, and pesticides. The tool also supports the real-time monitoring of crop performance. The technology has already digitalised 10,626 village-based advisors in six countries – Burkina Faso, Mali, Ghana, Nigeria, Mozambique, and Tanzania – where it supports delivery of inputs, services and information to 2.7 million farmers on nearly 600 million hectares of land. Overall, the World Economic Forum estimates that the adoption of precision agriculture on 15-25% of farms could boost global yield by 10-15% by 2030. It would also lead to a 10% reduction in greenhouse gas emissions and a 20% decrease in water usage.
The optimisation of agricultural value chains is critical in advancing food and nutrition sufficiency without increasing the size of land under cultivation. Technologies like blockchain and the Internet of Things (IoT) enable better tracking, traceability, and management of agricultural products throughout the value chain. This reduces post-harvest losses, optimises transportation routes, and ensures timely delivery, thereby lowering energy consumption and emissions.
A good example is the deployment of IBM technology in Rwanda that combines satellite data with machine learning to identify where maize is grown and the forecasted yield. Farmer organisations can also use the technology to identify areas of low yields and provide timely output-enhancing measures such as the adequate supply of fertilisers.
Yet, even with the transformative nature of the technologies, many remain beyond the reach of a vast majority of smallholder farmers in Africa due to the high costs of acquisition and lack of infrastructure to support such solutions. In the short-term, stakeholders can ensure an equitable and inclusive transition through investments in digital infrastructure and connectivity driven by a collaborative approach for developing a conducive policy environment, and the advancement of regional integration. Sustained investments in agricultural research and development also remain crucial, as has been shown in developed countries, which increased their adoption of agtech by committing 3.25% of their GDP compared to only 0.52% in developing countries. The increasing disparity in R&D expenditure exacerbates the gap in productivity, thereby rendering the poorest countries incapable of rapid progress.
The writer is a Senior Programme Office, AGRA
About The Author
