Diptanshu Mann
Topic
Model-Based Systems Engineering Framework for Maximizing Farm Operational Efficiency with Agricultural Autonomy Metrics
Currently working on:
Co-optimizing electric tractor powertrain design and farm operational efficiency
Agriculture faces mounting pressure to deliver higher productivity, precision and sustainability with fewer resources. Manual and semi-mechanized operations often fall short due to inefficient routes, uneven irrigation and inconsistent yield mapping which limits both output and environmental performance. Farmers and equipment developers need a clear, data driven framework to decide how much autonomy and system integration are necessary to maximize efficiency while reducing labor and emissions.
This research applies Model-Based Systems Engineering (MBSE) to design and evaluate autonomous farm operations. Using remote sensing inputs (e.g., NDVI, soil and topographic data), the study models workflows for route planning, irrigation management and grain storage optimization. It systematically compares semi-autonomous to fully autonomous configurations to determine the minimum autonomy level that achieves peak efficiency. The work further extends to conceptualizing a battery electric tractor and its supporting charging infrastructure, treating autonomy as an enabler for electrification. A complementary LLM based human–machine interface will enable real time decision support and automated reporting.
The framework creates a unified digital environment that brings autonomy, sustainability and energy optimization into one place. In practice, it is designed to deliver clear, measurable gains, including double digit reductions in operational time, labor and fuel or energy use. It also establishes objective autonomy benchmarks that can guide equipment investment and policy decisions, while opening practical pathways toward net zero, electrified farming with intelligent human machine collaboration and real time decision support.
By contrast, most existing studies treat problems in isolation, for example field navigation or irrigation, or they import generic autonomy scales from automotive contexts. These approaches miss the system of systems character of farming and overlook the interplay among data, energy and people. The MBSE driven framework addresses that gap by linking task level autonomy with energy architecture and operator interface design, yielding a holistic and transferable tool for the next generation of smart farming.
Key Words: Model-Based Systems Engineering (MBSE), SysML, Agricultural Levels of Autonomy, Operational Efficiency Framework, Precision Agriculture, Autonomous Farming Machinery