Back to search

South Dakota State University

Improving The Utility of Precision Agriculture Through Machine Learning and Climate-Smart Practices

Abstract

dc:description.abstract

Climate Smart Practices are management strategies that focus on increasing soil and crop productivity, utilize site-specific strategies to increase resiliency against the effects of climate change, and mitigate these negative effects by reducing greenhouse gas (GHG) emissions. Decision Support Systems (DSSs) using machine learning (ML) can adjust models based on new information and help farmers make climate smart decisions within their operation. The 4R nutrient management model of right source, rate, location, and time also demonstrates a framework that may be considered climate smart by improving soil and crop productivity. However, when initially conceptualized, the 4R model did not consider GHG emissions. Additionally, the long-term adoption of DSSs has been low in agriculture, reducing the ability of farmers to collect and analyze farm data to the fullest. Therefore, the objective of the first chapter is to examine applications of, and barriers to, DSSs in precision agriculture (PA). The objective of the second chapter evaluates the 4R model to determine the impact of GHG emissions when utilizing near continuous chambers over a two-year period. The GHG emissions were measured by analyzing nitrous oxide and carbon dioxide emissions from a 50/50 split application of 157 kg N/ha that was applied to corn (Zea mays) at pre-emergence and V6 compared to a single application at pre-emergence 157 kg N/ha in a two-year replicated study. Results from the first chapter identify the barriers preventing farmers from using DSSs as well as suggesting solutions to these challenges. Results from the second chapter indicate that the split application can reduce carbon dioxide and carbon equivalent emissions and therefore, may be a useful framework for DSSs to follow in achieving Climate Smart Practices.

Degree

thesis:*
Name thesis:degree_name
Master of Science (MS)
Level thesis:degree_level
Thesis - Open Access
Discipline thesis:degree_discipline
Agronomy, Horticulture, and Plant Science

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Brugler, Skye
Contributors dc:contributor
  • David Clay

Subjects

dc:subject × 7

Rights

dc:rights

Identifiers

dc:identifier.*
Repository record dc:identifier
https://openprairie.sdstate.edu/etd2/689

Chain of custody

source
Harvested from
South Dakota State University
Base URL
openprairie.sdstate.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Brugler, Skye. Improving The Utility of Precision Agriculture Through Machine Learning and Climate-Smart Practices. Thesis - Open Access thesis, https://openprairie.sdstate.edu/etd2/689