Expensive models and experiments
PIML can reduce repeated simulation or experimental cost while retaining the governing knowledge used in Agricultural Engineering.
Engineering Research Community
Agricultural Engineering & Physics-Informed Machine Learning
Physics-grounded modelling, learning and validation for Agricultural Engineering
Agricultural Engineering applies engineering to soil, water, crops, machinery, controlled environments, post-harvest systems, energy and environmental management. Modern work includes irrigation, drainage, soil and water conservation, precision agriculture, farm robotics, greenhouse control, remote sensing, agricultural structures and crop-process modelling.
Agricultural data are heterogeneous and strongly affected by location, weather, management and biological variability. Purely data-driven models can fit historical patterns but may violate water, energy or crop-process relationships and may fail in extreme or unseen seasons. PIML offers a way to combine observations with soil physics, hydrology, energy balances, crop models and machinery dynamics.
This page presents ten focused research areas, degree-level project pathways, selected publications and direct support through the PIMLS biweekly members meeting.
This Agricultural Engineering guide covers Physics-Informed Neural Networks (PINNs), physics-guided machine learning, scientific machine learning, neural operators, hybrid models and engineering digital twins. Explore the research and project pathways below, then join the Physics-Informed Machine Learning Society to connect with the international PIMLS community.
The central ideaEstablished Agricultural Engineering knowledge + measurements and simulation + machine learning
10focused research areas
3academic project pathways
6selected publications
Biweeklymember research meeting
Why this combination matters
Why Agricultural Engineering Needs Physics-Informed Learning
Use available scientific knowledge to make limited data more useful, transparent and testable.
Incomplete engineering models
Learn uncertain parameters, closures or discrepancies around an inspectable mechanistic foundation.
Transfer across conditions
Test whether structured models generalize across geometries, materials, assets, operating regimes or sites.
Trustworthy evidence
Use physical residuals, independent measurements, uncertainty and conventional engineering baselines before deployment.
Ten focused directions
Major Agricultural Engineering PIML Research Areas
Each card connects a meaningful Agricultural Engineering question with suitable scientific knowledge, modelling choices and evidence needed to test it.
01
Soil-Moisture Estimation
PIML can combine probes, weather, soil texture, remote sensing and Richards equation. The 2025 PINN-SM paper incorporates Richards equation for vadose-zone profiles: https://doi.org/10.1029/2024JH000547 Research should distinguish surface from root-zone moisture and validate at independent depths/sites.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
02
Infiltration and Drainage
Unknown hydraulic conductivity, retention parameters and preferential flow can be inferred from moisture/pressure observations. Identifiability and parameter correlation are major concerns.
Model and evidenceMechanistic and data-only baselines, uncertainty and independent validation
03
Root Water Uptake
Root uptake couples soil water, root distribution and plant demand. A PINN workflow has reconstructed uptake and saturation patterns from hydrogeophysical information: https://doi.org/10.1016/j.jhydrol.2025.134675
Model and evidenceGeometry, material or system parameters, sensor data and physical residuals
04
Irrigation Scheduling
The model should connect weather, soil storage, crop demand and irrigation constraints. Decision evaluation should report water use, stress/yield proxy and robustness—not only moisture RMSE.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
05
Evapotranspiration
The 2019 physics-constrained ET study combines ML with an energy-conserving Penman–Monteith-like structure and reports better extrapolation than pure ML: https://doi.org/10.1029/2019GL085291 This paper is a foundational example of agricultural/environmental PIML because it learns a difficult process…
Model and evidenceMechanistic and data-only baselines, uncertainty and independent validation
06
Hydrology and Watershed Processes
Differentiable hydrologic models retain process states while optimising parameters with gradient-based learning. The HESS study discusses the suitability of differentiable PIML hydrologic models: https://doi.org/10.5194/hess-27-2357-2023 Agricultural relevance includes irrigation supply, drainage, runoff,…
Model and evidenceGeometry, material or system parameters, sensor data and physical residuals
07
Crop Growth Modelling
Process models such as AquaCrop, DSSAT, APSIM or WOFOST describe phenology, biomass and yield with different levels of detail. PIML can estimate uncertain parameters, correct model discrepancy, assimilate observations or emulate expensive ensembles.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
08
Crop-Yield Forecasting
Physics-informed yield work can use water balance, crop-stage constraints, nitrogen relations or process-model outputs. A recent regional maize scheme combines the SWAP model, data assimilation, remote sensing and ML emulators: https://www.sciencedirect.com/science/article/pii/S0168169925012487 Evaluation…
Model and evidenceMechanistic and data-only baselines, uncertainty and independent validation
09
Precision Agriculture and Remote Sensing
Radiative-transfer models relate vegetation/soil states to observed reflectance or microwave response. Hybrid inversion can retain measurement physics while learning uncertain canopy/soil components.
Model and evidenceGeometry, material or system parameters, sensor data and physical residuals
10
Soil-Moisture Remote Sensing
Physics-informed retrieval can combine multisensor satellite data with scattering/radiative models. One example uses physics-informed ML with Sentinel imagery for soil moisture in support of hydrology and agriculture: https://abhilashsingh.net/docc/PIMLSM.pdf
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
Choose the right research depth
Projects for Every Academic Stage
Start with a scope that matches your time, mathematical background, experimental access and expected research contribution.
Project pathway 1
B.E./B.Tech
Learn the foundations with a bounded, measurable system.
- Physics-guided field water balance.
- Evapotranspiration hybrid regression.
- Greenhouse thermal model.
- Soil-moisture profile PINN benchmark.
- Tractor energy/fuel model with learned residual.
Expected outcome
A reproducible implementation, clear baselines, a manageable dataset and physically meaningful validation.
Project pathway 2
M.Tech
Combine an engineering model, substantial data and rigorous comparison.
- Remote-sensing/process-model crop assimilation.
- Root-water-uptake inverse problem.
- Physics-informed irrigation optimiser.
- Controlled-environment digital twin.
- Nutrient-transport parameter estimation.
Expected outcome
A thesis-quality study with held-out regimes, mechanistic and data-only baselines, ablation and uncertainty.
Project pathway 3
Ph.D.
Address a publishable methodological, multiscale or deployment research gap.
- Differentiable soil–plant–atmosphere modelling.
- Multi-site uncertainty-aware crop forecasting.
- Multi-fidelity agricultural remote sensing.
- Physics-informed farm robotics and decision support.
- Climate-extreme generalisation with process constraints.
Expected outcome
New methodology or validated engineering insight, multi-regime evidence, reproducible software and journal publications.
From idea to evidence
A Strong PIML Project Workflow
01
Define
Choose one Agricultural Engineering question and a measurable engineering output.
02
Model
State the governing relationships, constraints or validated domain knowledge you will retain.
03
Compare
Build mechanistic and data-only baselines before the hybrid model.
04
Validate
Hold out experiments, conditions, assets, sites or regimes at the deployment level.
05
Publish
Report uncertainty, ablation, limitations, data lineage and reproducible code.
Read before you modelDiscuss Your Literature
Selected Publications and Why They Matter
Use this focused reading list to understand the general PIML framework, direct Agricultural Engineering evidence and suitable hybrid modelling methods.
Literature review advice
Do not list papers only. Compare the engineering question, incorporated knowledge, data, split strategy, baselines, uncertainty and evidence level.
This source is included in the Agricultural Engineering literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Agricultural Engineering.
Read publication or record This source is included in the Agricultural Engineering literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Agricultural Engineering.
Read publication or record This source is included in the Agricultural Engineering literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Agricultural Engineering.
Read publication or record This source is included in the Agricultural Engineering literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Agricultural Engineering.
Read publication or record This source is included in the Agricultural Engineering literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Agricultural Engineering.
Read publication or record This source is included in the Agricultural Engineering literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Agricultural Engineering.
Read publication or record Build an interdisciplinary team
Where Agricultural Engineering Can Collaborate
Computer Science
Scientific ML, optimization, trustworthy AI and reproducible research software.
Applied Mathematics
Differential equations, numerical methods, inverse problems and uncertainty.
Sensing & Control
Instrumentation, data acquisition, state estimation and responsible deployment.
Domain Laboratories
Experiments, calibration, validation evidence and practical expertise for Agricultural Engineering.
Before you begin
Frequently Asked Research Questions
These answers help students avoid common scope, terminology and validation mistakes.
Still have a question?
Use the biweekly meeting form for research guidance.
Request accessNo. Agricultural Engineering projects may use physics-guided features, hybrid residual models, differentiable simulators, neural operators, constrained architectures or data assimilation. State exactly what knowledge is incorporated.
Choose one engineering question, a measurable output and a defensible mechanistic baseline. Add learning only where data can identify an uncertainty or discrepancy.
A meaningful question, justified prior knowledge, deployment-level holdouts, strong baselines, ablation, uncertainty, reproducibility and honest limitations.
Simulation can broaden coverage, but simulation-only evidence cannot establish real-system accuracy. Use calibrated experiments, field measurements or trusted independent references appropriate to the claim.
Submit the biweekly members meeting form to discuss your project level, branch, data, model, validation plan and possible collaborators.
Take the next step
Bring your Agricultural Engineering research idea to PIMLS
Join the biweekly members meeting for project guidance, collaboration and publication planning—or contact the Society directly.
Meeting participation is requested through the Google form. Complete it carefully so the Society can understand your research interest.