Enhancing Precision Agriculture Decision Making for the AgriSenze™ Soil Nutrient Monitoring System Through Big Data Analytics

Abstract

In this master's thesis, I developed an agricultural big data analytics platform. First, I built a web application programming interface (API) backend platform to collect and aggregate diverse semi-structured agricultural data from various data sources. I then generated an agricultural big dataset that can be utilized by precision agriculture solutions like AgriSenze™ for various decision-making purposes. Finally, I manipulated the big dataset primarily collected from the Norwegian University of Life Sciences (NMBU) to build an ensemble stacking regressor machine learning algorithm for predicting daily soil temperatures at six different depths (2 cm, 5 cm, 10 cm, 20 cm, 50 cm, and 100 cm). This daily soil temperature forecast model is also integrated with the web API platform, enabling cloud access by any precision agriculture solution, specifically by the AgriSenze™ plant nutrient management solution.

The entire solution, encompassing data collection, aggregation, storage, data analytics, and daily soil temperature prediction, is ready for integration with the AgriSenze™ cloud solution powered by DjuliTM, an IoT solution developed by Zimmer and Peacock AS