Research archive

A WeChat Mini Program for plant phenotyping fieldwork: leaf-angle and land-area measurement, site weather, image analysis, AI-assisted charting and data management in one mobile toolkit.

A web application and batch pipeline that removes plant-image backgrounds without task-specific training, using a multimodal image model with a structured prompt, aspect-ratio matching and file-signature format detection.

A desktop platform that processes hyperspectral, LiDAR, RGB and thermal phenotyping data with one interface, interactive parameter tuning, batch processing and structured exports.

A measuring and analysis framework that predicts leaf BRDF parameters from phenotypic traits in four species, combining directional spectroscopy, Cook–Torrance fitting, ensemble learning and canopy ray tracing (Plant Phenomics, 2025).

A practical path from a local Ollama assistant to retrieval and controlled tool use, with explicit privacy, security, versioning, and deployment boundaries.

A local OpenCV method that segments separated plant samples on a uniform background and measures size, shape and colour in calibrated units, with an overlay for every image.

A concise, publisher-neutral guide to journal selection, manuscript preparation, submission, peer review, publication status, research integrity, and post-publication maintenance.

Generating 3D cotton plants from single photographs with 3D generative AI and evaluating them organ by organ against multi-view SfM reconstructions of the same plants.

A UAV workflow for plot-level 3D crop phenotyping: Cross-Circular Oblique flight design, SfM reconstruction, canopy point-cloud processing with CanopyPC, and machine-learning models of crop traits.

An interactive OpenCV tool that turns raw root scans and photographs into clean binary images through polygon ROI selection, illumination correction, thresholding and brush-based correction, ready for root-trait software.

A maintainable workflow for choosing a local model, testing it with Ollama, planning parameter-efficient fine-tuning, evaluating results, and exposing a service safely.

A modular model that reconstructs crop plants from multi-view images, assembles a triangle-facet canopy, simulates its light distribution by ray tracing, and integrates leaf photosynthesis to canopy carbon gain.

Processing DJI P4 Multispectral imagery into radiometrically documented orthomosaics in WebODM, checking bands in QGIS, and extracting plot-level vegetation indices and texture features.

A concise, reproducibility-focused route from tensors and training loops to transfer learning, evaluation, safe checkpoints, and deployment boundaries.

A growth-chamber protocol that reconstructs potted cotton plants from two-elevation turntable video with structure from motion, with scale control, colour correction and accuracy assessment.

A practical workflow for structuring Python research projects, recording environments, collaborating through Git, and preserving data provenance.

A safe, modern introduction to repositories, commits, branches, remotes, pull requests, authentication, and undoing mistakes.

A compact, safety-aware reference for everyday macOS, Finder, text-editing, browser, screenshot, and recovery shortcuts.

A version-aware workflow for creating a Docusaurus portfolio, configuring GitHub Pages correctly, and maintaining a reliable deployment.