01Images to traits
Build a phenotyping workflow
Start with reproducible image analysis, add foundation-model segmentation, then benchmark on field data.
- PlantCV
- Meta SAM 3.1
- PhenoBench
Research learning hubCurated and verified · July 2026
Learn AI for Science & digital agriculture.
A focused map of official courses, models, datasets, and tools for scientific machine learning, AI agents & LLMs, crop simulation, plant phenotyping, remote sensing, and 3D reconstruction.
- curated resources
- 50
- focused topics
- 6
- source policy
- official-first
- last verified
- July 2026
Start with a goal
Three practical learning paths
Each path moves from a reliable starting point to a reproducible research workflow.
02Process to prediction
Learn process-based crop models
Move from an approachable water-productivity model to Python workflows and full cropping-system simulation.
- FAO AquaCrop
- PCSE / WOFOST
- APSIM Next Generation
03Models with mechanisms
Enter AI for Science
Map the field, learn scientific machine learning, then reproduce a domain model with official notebooks.
- AI for Science 101
- MIT SciML
- NVIDIA PhysicsNeMo
Curated catalog
Find the right resource
Search by name or topic, then narrow the catalog by field and experience level.
Showing 50 of 50 resources
AI4Science101 CommunityCommunity
AI for Science 101
A readable field map spanning graph learning, molecular simulation, causal ML, structural biology, and quantum science.
- Field map
- Reading
MIT 18.337Official
Updated 2026MIT Parallel Computing & SciML
A rigorous course on automatic differentiation, ODE/PDE solvers, PINNs, probabilistic programming, GPUs, and HPC.
- PINN
- Differential equations
- HPC
NVIDIAOfficial
Updated 2026NVIDIA PhysicsNeMo
Production-grade Physics AI tutorials for neural operators, PINNs, MeshGraphNet, weather, fluids, and molecular systems.
- Physics ML
- Neural operators
- Python
DeepChemOfficial
Updated 2026DeepChem Tutorials
Notebook-first learning for molecular property prediction, drug discovery, quantum chemistry, and materials science.
- Molecules
- Materials
- Notebooks
Chan Zuckerberg BiohubOfficial
Updated 2026Biohub ESM
Current ESM code for protein language models, embeddings, structure prediction, and protein interaction research.
- Protein LM
- ESMC
- ESMFold2
Google DeepMindOfficial
AlphaFold Server & Database
Explore predicted protein structures and test biomolecular interactions with AlphaFold 3 through the official server.
- Structural biology
- Protein
Microsoft Research AI for ScienceOfficial
Updated 2026Microsoft Aurora
A foundation model for weather, air quality, waves, and tropical cyclones, with official ERA5 examples.
- Earth systems
- Weather
- Foundation model
FutureHouseOfficial
Updated 2026PaperQA2
A citation-grounded literature search and scientific question-answering workflow that can also use local models.
- Literature
- RAG
- Research agents
APSIM InitiativeOfficial
Updated 2026APSIM Next Generation
Model soil, water, nitrogen, crops, rotations, and management scenarios in a mature agricultural systems framework.
- Systems model
- Scenario analysis
DSSAT FoundationOfficial
Updated 2026DSSAT Cropping System Model
Learn genotype–soil–weather–management simulation for yield forecasting, cultivar calibration, and climate risk studies.
- Yield
- Calibration
- Climate risk
Wageningen modelling communityOfficial
Updated 2026PCSE / WOFOST
A Python crop simulation environment with WOFOST, LINGRA, and LINTUL—well suited to optimization and data assimilation.
- Python
- WOFOST
- Data assimilation
CropboxOfficial
Cropbox.jl
A declarative Julia framework for building, calibrating, evaluating, and visualizing crop and physiological models.
- Julia
- Model development
- Experimental
FAO Land and WaterOfficial
FAO AquaCrop 7.1
An approachable crop water-productivity model with official handbooks, reference manuals, and 43 video tutorials.
- Water productivity
- Irrigation
BioCroOfficial
Updated 2026BioCro
Modular C++ and R crop-growth simulation with practical guides for photosynthesis, environment, and model development.
- R
- C++
- Photosynthesis
Donald Danforth Plant Science CenterOfficial
Updated 2026PlantCV
Reproducible RGB, NIR, thermal, fluorescence, hyperspectral, morphology, and geospatial plant-image workflows.
- Python
- Image analysis
- Hyperspectral
PhenoCam workflowOfficial
PhenoAI
A focused workflow for PhenoCam time-series quality control, vegetation segmentation, indices, and phenology extraction.
- Phenology
- Time series
- DeepLabV3+
University of Bonn / PhenoRobOfficial
Updated 2026PhenoBench
A field benchmark for crop, weed, plant-instance, leaf-instance, and hierarchical panoptic segmentation from UAV imagery.
- UAV
- Segmentation
- Codabench
ICRISATOfficial
Updated 2025ICRISAT Legume 3D Point Clouds
Multispectral 3D scans of four legume crops with organ-level leaf, petiole, and stem labels plus MIAPPE metadata.
- Point cloud
- Organ labels
- MIAPPE
Meta ResearchOfficial
Updated 2026Meta SAM 3.1
Concept-prompted detection, segmentation, and tracking for images and video, with notebooks and fine-tuning code.
- Segmentation
- Tracking
- Foundation model
Kreshuk LabOfficial
Updated 2025PlantSeg v2
Napari-based 2D and 3D cell segmentation tuned for densely packed plant tissues and microscopy workflows.
- Microscopy
- 3D cells
- Napari
John Innes CentreOfficial
MorphoGraphX
Visualize and quantify 4D live-imaged tissues, cell geometry, growth, fluorescence, and morphogenesis.
- 4D imaging
- Morphogenesis
- Cells
Open3DOfficial
Open3D Tutorials
Python and C++ tutorials for point clouds, meshes, RGB-D data, registration, reconstruction, and 3D machine learning.
- Point cloud
- Mesh
- 3D vision
IBM / NASA / TorchGeoOfficial
Updated 2026TerraTorch + Prithvi-EO-2.0
Fine-tune open geospatial foundation models for multi-temporal classification and segmentation, including crop mapping.
- Earth observation
- HLS
- Foundation model
NASA HarvestOfficial
Updated 2026NASA Harvest Presto
A lightweight self-supervised time-series transformer for Sentinel-1/2, weather, and terrain in low-label crop mapping.
- Time series
- Few-shot
- Crop mapping
Google Earth EngineOfficial
Updated 2025AlphaEarth Satellite Embeddings
Annual precomputed Earth representations for few-shot classification, clustering, land cover, and agricultural mapping.
- Embeddings
- Few-shot
- Earth Engine
European Space AgencyOfficial
Updated 2026ESA WorldCereal
Global crop extent and crop-type mapping with a MOOC, reference data, notebooks, and a processing hub.
- Global crops
- MOOC
- Processing hub
WorldCereal / open communityOfficial
Updated 2026Fields of The World
Global field-boundary data, pretrained segmentation models, CLI, QGIS tooling, and browser inference.
- Field boundaries
- Segmentation
- QGIS
NASA EarthdataOfficial
NASA ARSET: ML for Agriculture
A complete remote-sensing ML workflow using Sentinel-2, crop labels, cloud data engineering, and TensorFlow.
- Remote sensing
- Cloud
- Crop classification
FAOOfficial
FAO SEPAL Classification
A low-code workflow for mosaics, training samples, and RF/SVM/gradient-boosting land and crop classification.
- Low code
- Sentinel
- Classification
Google for DevelopersOfficial
Google Earth Engine Tutorials
Official JavaScript and Python learning paths for planetary-scale imagery, time series, classification, and export.
- Geospatial
- JavaScript
- Python
OpenDroneMap CommunityOfficial
OpenDroneMap
Turn drone imagery into orthophotos, point clouds, DSM/DTM, multispectral products, and textured 3D models.
- UAV
- Photogrammetry
- Point cloud
PyTorch FoundationOfficial
Updated 2026PyTorch Tutorials
The official path from tensors and training loops to transfer learning, detection, distributed training, and compilation.
- Deep learning
- Python
- Computer vision
PyG TeamOfficial
Updated 2026PyTorch Geometric
Hands-on graph neural networks for molecules, biological networks, meshes, point clouds, and heterogeneous graphs.
- GNN
- Molecules
- Point clouds
Stanford UniversityOfficial
Updated 2026Stanford CS224W
A structured course on graph representation learning, GNNs, graph transformers, knowledge graphs, and applications.
- Graphs
- GNN
- Theory
Stanford UniversityOfficial
Stanford CS231n
A durable computer-vision foundation covering recognition, optimization, CNNs, transformers, detection, and segmentation.
- Computer vision
- Segmentation
- Transformers
Inria / Scikit-learnOfficial
Scikit-learn MOOC
A careful introduction to tabular ML, evaluation, pipelines, model selection, and leakage-aware experimentation.
- Classical ML
- Evaluation
- Pipelines
AnthropicOfficial
Updated 2026Anthropic Claude Docs
Official Claude developer docs: Messages API, tool use, extended thinking, structured outputs, prompt caching, and agent patterns.
- LLM API
- Tool use
- Prompting
OpenAIOfficial
Updated 2026OpenAI Platform Docs
Official OpenAI developer reference for the Responses API, function calling, structured outputs, embeddings, and retrieval.
- LLM API
- Function calling
- Embeddings
AnthropicOfficial
Updated 2026Claude Agent SDK
Build production agents on the same harness as Claude Code, with subagents, sessions, tool orchestration, and MCP support.
- Agents
- Python & TS
- MCP
OpenAIOfficial
Updated 2026OpenAI Agents SDK
A lightweight framework for multi-agent workflows with handoffs, guardrails, sessions, and built-in tracing.
- Agents
- Orchestration
- Tracing
MCP ProjectOfficial
Updated 2026Model Context Protocol
The open standard for connecting LLMs to tools and data sources, with a growing ecosystem of interoperable servers.
- Interoperability
- Tools
- Standard
Hugging FaceOfficial
Updated 2026Hugging Face Agents Course
A hands-on course on building agents with smolagents, LlamaIndex, and LangGraph, from fundamentals to a capstone project.
- Agents
- Hands-on
- Frameworks
LangChainOfficial
Updated 2026LangGraph
A low-level orchestration framework for durable, stateful multi-agent systems with explicit graphs, memory, and human-in-the-loop.
- Stateful agents
- Graphs
- Python
Hugging FaceOfficial
Updated 2026smolagents
A minimal library for code-writing agents—define tools, pick any model, and run agentic loops in a few lines of Python.
- Code agents
- Lightweight
- Python
Shanghai AI LabOfficial
Updated 2024SeedLLM 丰登
The first seed-industry LLM, trained for variety selection, agronomic traits, cultivation, and promotion-region reasoning.
- Agri LLM
- Breeding
- Chinese
AgriAgent (open source)Community
Updated 2024AgriAgent
An open Chinese agricultural multimodal model on MiniCPM-Llama3-V that diagnoses crop disease and answers farming questions.
- Agri VLM
- Disease ID
- Chinese
AgriGPT (arXiv)Community
Updated 2025AgriGPT
A domain LLM ecosystem for agriculture built on a multi-agent data engine and the Agri-342K instruction dataset.
- Agri LLM
- Dataset
- Ecosystem
Lilian WengCommunity
Updated 2026Lil'Log
In-depth technical essays on LLM agents, diffusion, RL, hallucination, and reasoning—widely used as reference explainers.
- Deep dives
- LLM agents
- Reference
Andrej KarpathyCommunity
Updated 2026Neural Networks: Zero to Hero
Build neural networks from scratch—backprop, makemore, and a GPT—through carefully narrated, code-along video lectures.
- From scratch
- Backprop
- GPT
3Blue1BrownCommunity
Updated 20263Blue1Brown: Neural Networks
Visual, intuition-first explanations of neural networks, gradient descent, backpropagation, and transformers.
- Intuition
- Visualization
- Math