Given the nonlinearity of the interaction between weather and soil variables, a novel deep neural network regressor (DNNR) was carefully designed with considerations to the depth, number of neurons of the hidden layers, and the hyperparameters with their optimizations. Additionally, a new metric, the average of absolute root squared error (ARSE) was proposed to address the shortcomings of root mean square error (RMSE) and mean absolute error (MAE) while combining their strengths. Using the ARSE metric, the random forest regressor (RFR) and the extreme gradient boosting regressor (XGBR), were compared with DNNR. The RFR and XGBR achieved yield errors of 0.0000294 t/ha, and 0.000792 t/ha, respectively, compared to the DNNR(s) which achieved 0.0146 t/ha and 0.0209 t/ha, respectively. All errors were impressively small. However, with changes to the explanatory variables to ensure generalizability to unforeseen data, DNNR(s) performed best. The unforeseen data, different from unseen data, is coined to represent sudden and unexplainable change to weather and soil variables due to climate change. Further analysis reveals that a strong interaction does exist between weather and soil variables. Using precipitation and silt, which are strong-negatively and strong-positively correlated with yield, respectively, yield was observed to increase when precipitation was reduced and silt increased, and vice-versa.

This paper explores the transformative potential of artificial intelligence (AI) in the context of sustainable agricultural development across diverse regions in Africa. Delving into opportunities, challenges, and impact, the study navigates through the dynamic landscape of AI applications in agriculture. Opportunities such as precision farming, crop monitoring, and climate-resilient practices are examined, alongside challenges related to technological infrastructure, data accessibility, and skill gaps. The article analyzes the impact of AI on smallholder farmers, supply chains, and inclusive growth. Ethical considerations and policy implications are also discussed, offering insights into responsible AI integration. By providing a nuanced understanding, this paper contributes to the ongoing discourse on leveraging AI for fostering sustainability in African agriculture.

Ranveer Chandra is the managing director of Research for Industry and leads Networking Research at Microsoft Research in Redmond, WA, USA. His research has shipped in multiple Microsoft products, including Xbox, Azure, and Windows. Stewart Collis is senior program officer for Digital Agriculture Solutions at the Bill and Melinda Gates Foundation where he focuses on digital farmer services, smart farming, and digital support systems for small-scale crop and livestock producers in low- and middle-income countries.

Agriculture finance represents an important element of eradicating extreme poverty and boosting shared prosperity. According to the International Fund for Agricultural Development, smallholders manage over 80% of the world's estimated 500 million small farms and provide over 80% of the food consumed in a significant part of the developing world, making a major contribution to poverty reduction and food security. Most smallholder farms are in Asia and sub-Saharan Africa, and in both regions over 80% of farmland is managed by smallholders. Even though these farmers are generally characterized by limited resources--particularly in terms of land--and dependence on household members for farm labor, they represent a critical part of food systems in developing countries. In light of the size and importance of the smallholder farming sector, the development community has a growing focus on providing these farmers with the funding they need to thrive.

How does artificial intelligence-powered precision farming affect food sustainability? This is the question we asked our panel of experts. "Precision farming" is a bit of a buzz phrase; it is often used, but rarely defined. Generally, it means the widespread adoption of new technologies to accurately monitor and control agricultural activity. But which technologies are adopted and which consequences result?

"AI is the broader concept of machines being able to carry out tasks in a way that is considered smart. The smart processes include machines being able to function automatically, reason and learn by themselves," explains Claudia Ayin, an independent ICT consultant. Machine learning is the aspect of AI that allows computers to learn by themselves. "Machine learning is therefore a branch of AI that is able to process large data sets and let machines learn for themselves without having been explicitly programmed," she adds. According to MarketsandMarkets, an Indian research company, in 2018 the worldwide AI in agriculture market was valued at €545 million and, by 2025, is expected to reach €2.4 billion as more and more smallholder farmers adopt new, data-driven technologies.

From smart factories and smart cities to virtual personal assistants and self-driving cars, artificial intelligence (AI) and the Internet of Things (IoT) are transforming how people around the world live, work, and play. But fundamentally changing the ways people, devices, and data interact is not simple or easy work. Microsoft's AI & IoT Insider Labs was created to help all types of organizations accelerate their digital transformation. Member organizations around the world get access to support both technology development and product commercialization, for everything from hardware design to manufacturing to building applications and turning data into insights using machine learning. Here's how AI & IoT Insider Labs is helping one partner, SunCulture, leverage new technology to provide solar-powered water pumping and irrigation systems for smallholder farmers in Kenya.

This blog post was authored by Peter Cooper, Senior Product Manager, Microsoft IoT. From smart factories and smart cities to virtual personal assistants and self-driving cars, artificial intelligence (AI) and the Internet of Things (IoT) are transforming how people around the world live, work, and play. But fundamentally changing the ways people, devices, and data interact is not simple or easy work. Microsoft's AI & IoT Insider Labs was created to help all types of organizations accelerate their digital transformation. Member organizations around the world get access to support both technology development and product commercialization, for everything from hardware design to manufacturing to building applications and turning data into insights using machine learning.

Imagine a world where blockchain allows migrants to securely and instantly send money home without any transfer fees. Or consider the possibilities if artificial intelligence algorithms capable of analyzing satellite imagery could enable smallholder farmers to get non-predatory loans without the need for a credit score. If these visions excite you, you're not alone – they were key topics of discussion amongst a group of leaders in financial inclusion from around the world at the latest Rethinking Financial Inclusion program at Harvard Kennedy School in October. Rethinking Financial Inclusion is an executive program presented by Evidence for Policy Design (EPoD) in collaboration with Harvard Kennedy School Executive Education. It combines data and an evidence-based problem solving approach to explore frontier issues in finance for individuals who are underserved.

Why data could be the deciding factor in Africa's agricultural transformation. The world has a palm oil problem. It's a global, billion-dollar industry and its end result is irreversible environmental damage, ranging from deforestation and fires, to the loss of species such as tigers, pygmy elephants and orangutans. Palm oil is used in 50% of the products we buy (think bread, shampoo, soaps and even chocolate) due to the fact that it is the highest-yielding vegetable oil crop. Yet, in a country like Uganda, where 80% of the population is involved in agriculture as a way of life, many Ugandans farm oil palm on small plots, barely making a living. "The use of data for purposes of precision agricultural systems is being used around the world to optimize farms, from anticipating natural disasters such as droughts and flooding, to predicting the best time to harvest crops, to anticipating outbreaks of pests and disease before they impact the produce," says AgriSA's Janse Rabie.