A Review of Yield Forecasting Techniques and Their Impact on Sustainable Agriculture

Sustainable agricultural production plays a key role in ensuring food security and aligns with the 2030 global sustainable development goals (SDGs). Advances in technology and increased data access provide vital support to sustainable agriculture and enhance cost-effective crop production. Crop yield is a crucial metric for agricultural resiliency and food security. The precision of yield forecasting plays a significant role in enhancing crop productivity, streamlining harvest operations, and reducing production losses. Given the increasing global food demand and limited agricultural land availability, inaccurate forecasts have a greater impact on the supply chain because of the resources wasted, operational inefficiencies, and increased production costs. We review multiple yield estimation approaches, ranging from traditional statistical methods to advanced machine learning algorithms. We focus on highly scalable methods that can be applied to different croplands and center our analyses on the biophysical foundation behind the major available techniques; this is often linked with forecasting accuracy. By comprehensively reviewing these methodologies and the biophysical links behind crop productivity, we aim to shed light on their strengths, limitations, and applicability in various agricultural contexts. We delve into the criticality of precise yield predictions, emphasizing their impact on the supply chain and commodity markets. Finally, we highlight the need for continuous research and innovation in this area. We emphasize the importance of accurate and scalable field representations and forecasts for driving sustainable and cost-effective agricultural production.