Sustainable beet farming productivity regulations and digital farming techniques development
Project no. 22171 · Status: Kapanmış (Yayın bekleniyor) · 2020
Summary
<p>Climate change, socio-economic developments, and an increasing population are exerting intense pressure on available resources for food production, especially on resources such as agricultural lands and water. To adapt to the need for doubling agricultural production by 2050, the development of risk management and resource optimization methods at the field and farm levels is of great importance.</p><p>Our project aims to achieve more resilient agricultural production by reducing risks in production and optimizing resources through the development of a seasonal multi-parameter model. To develop this innovative model, the physicochemical properties of soil, the geomorphological properties of fields (soil depth, the geological parent material of soil, land slope characteristics, etc.), parcel-level crop pattern history, and climate forecasts for the upcoming growing seasons will be examined together. Seasonal plant and soil management not only assists in resource optimization for sustainability but also contributes to food security by managing risks on yield amounts. Increased predictability in production also encourages family farmers to have a better future and develop a future-proof business model. From a climate resilience perspective, our project will promote adaptation to climate change and reduce the carbon footprint per unit of sugar beet cultivation.</p><p>Considering the agronomically demanding nature of sugar beet (a rotational crop requiring sustainable management) and its economic value (a yearly value of $1.2 billion in the Turkish economy), this project has been specifically designed for sugar beet and implementation in a pilot region. However, the applicability and scalability of the solution to larger areas and other arable crops are also targeted for future work. Therefore, scalable and accurate data sources such as multispectral satellite imagery, digital soil maps, and local weather forecasts have been selected and investigated with an interdisciplinary approach to achieve more sustainable agricultural production habits."</p><p>Keywords: Sugarbeet, productivity, remote sensing technique, crop monitoring, machine learning. </p>