Curriculum Vitae

Personal Information​

Liangchao Deng (邓良超)

🔊

Joint Ph.D. Candidate in Crop Science (SHZU × CAS-CEMPS)

2023 – 2026 (expected)

🔎 Scholar🟢 ORCID🧪 RG🐙 GitHub

Academic Profiles:

• ORCID: 0000-0002-5194-0655
• Google Scholar: Profile
• ResearchGate: Profile

Education​

Ph.D. Candidate in Crop Science | 2023 – 2026 (expected) College of Agriculture, Shihezi University, Shihezi, Xinjiang, China (Joint Ph.D. Training with the Center for Excellence in Molecular Plant Sciences, Chinese Academy of Sciences, Shanghai, China)

• Supervisors: Prof. Yali Zhang (SHZU) & Dr. Qingfeng Song (CAS-CEMPS)
• Collaborating PI: Prof. Xinguang Zhu (CAS-CEMPS)
• Thesis: Research on the optimization of cotton canopy structure and photosynthetic efficiency improvement based on multi-scale three-dimensional reconstruction and ray tracing

B.Sc. in Information and Computational Science | 2016 – 2021
College of Science, Shihezi University, Xinjiang, China

• Core Courses: Numerical Solution of Differential Equations, Optimization Methods, Data Structures, Probability and Statistics, Mathematical Modeling
• Undergraduate Thesis: Numerical Solution of Phase Transition Equations
• Research Training: Focused on computational mathematics and numerical simulation, with applications in solving nonlinear partial differential equations.

Research Interests​

Cutting-Edge Technology Focus​

• Generative AI for Agriculture: Image-to-3D plant modeling; foundation models for crop phenotyping; multimodal systems
• Advanced Computer Vision: SFM, NeRF, 3D Gaussian Splatting, differentiable rendering for plant/canopy reconstruction based on cameras/UAV
• AI-Assisted Scientific Computing: LLM integration in research workflows; AI-assisted code generation for phenotyping pipelines
• Digital Agriculture Innovation: IoT sensor; real-time monitoring

Core Research Domains​

• Precision Phenomics: High-throughput phenotyping using UAVs, hyperspectral/multispectral imaging, and LiDAR point clouds
• Computational Plant Biology: Ray-tracing photosynthesis models; BRDF-based optical simulations
• Environment-Smart Agriculture: AI-driven crop adaptation strategies; predictive modeling for environmental resilience

Innovation and Impact​

• Bridging newest technology with practical agricultural solutions
• Developing scalable technologies for global food security
• Creating open-source tools for the international ag-research community

Research Experience​

Generative AI for Agricultural Applications | 2024 – Present​

• Innovation: Built image-to-3D generative workflows (diffusion, NeRF) for rapid plant architecture synthesis, Establish a general crop crown photosynthetic prediction model based on multi-modal phenotype data
• AI Integration: Fine-tuned LLMs for domain-specific analysis and automated research pipelines
• Technical Achievement: AI-assisted coding framework accelerating phenotyping algorithm development
• Impact: Reduced 3D plant model generation from days to minutes, enabling near-real-time digital twins

Next-Generation Phenotyping with Advanced Computer Vision | 2021 – Present​

• Implemented 3D Gaussian Splatting and differentiable rendering for photorealistic plant/canopy reconstruction
• Deployed multi-view stereo (SfM/MVS) and LiDAR for high-fidelity structure capture and trait extraction
• Based on the three-dimensional point cloud model and ray tracing algorithm of plants, build a cotton canopy photosythetic model and simulate the space-time distribution of canopy light and photosynthesis.
• Explored the optimal combination of plant architecture and agronomic practices with maximum photosynthetic rate as the objective
• According to the working principle of real lidar, use ray tracing algorithms to build virtual lidar, simulate radar scanning plant canopy, and obtain a large number of synthetic data training models, accelerate the development of the phenotype platform

Technical Expertise​

Artificial Intelligence & Machine Learning​

• Deep Learning: PyTorch, TensorFlow, Transformers, CUDA
• Generative AI: Diffusion models, NeRF, 3DGS, text-/image-to-3D
• Foundation Models: LLM fine-tuning, CLIP, prompt engineering
• MLOps: Docker, distributed training on multi-GPU

Advanced Computer Vision & Graphics​

• 3D Reconstruction: SfM/MVS, 3DGS, photogrammetry, point-cloud processing
• Rendering: Ray tracing
• Real-time Processing: OpenCV, CUDA/TensorRT; edge deployment (NVIDIA Jetson)
• Libraries/Tools: Open3D, PCL, Blender Python API, Three.js (web viz)

High-Performance Computing & Cloud​

• Programming: Python, MATLAB, R
• DevOps: Git, containerization; parallel data processing on HPC

Agricultural Technology​

• Remote Sensing: RGB / multispectral / hyperspectral / thermal; LiDAR; UAV systems
• Sensor Networks: IoT devices for microclimate & photosynthesis monitoring
• Data Standards: GeoTIFF and common ag-data exchange formats

Research & Development Tools​

• Scientific Computing: Python, MATLAB, R; numerical modeling
• Collaboration: GitHub, Slack, Notion; academic writing (Markdown, Overleaf)
• Project Management: Agile/Scrum; reproducible research workflows

Publications & Research Output​

1. Deng, L., Yu, L. X., Mao, L., Wang, Y., Guo, X., Wang, M., Zhang, Y., Song, Q., Zhu, X.-G. (2025). Leaf Optical Properties Predicted with BRDF and Phenotypic Traits in Four Species: Development of Novel Analysis Tools. Plant Phenomics DOI:10.1016/j.plaphe.2025.100135 PDF

Teaching and Mentoring Experience​

Student Mentoring​

• Yu Jingxuan | Undergraduate Research | 2023 – 2025 Project: Field-scale 3D reconstruction & quantitative analysis of cotton varieties (UAV) Role/Outcome: Guided MVS pipeline; student gained 3D modeling & data-analysis proficiency
• Zhang Rongze | Undergraduate Research | 2023 – 2025 Project: Single-plant 3D reconstruction & morphological quantification Role/Outcome: Contributed to automated phenotyping workflow
• Xie Hejiang | Undergraduate Research | 2023 – 2025 Project: Cotton yield response under nitrogen treatment regimes Role/Outcome: Trained in experimental design & statistics; results supported N optimization

Mentoring Philosophy: Hands-on learning; rigorous experimental design; integration of computation with agronomy; reproducible, open science.

Innovation & Entrepreneurship​

Open-Source Contributions​

• Stereo-Vision-Camera-Box · Python, Computer Vision Advanced stereo-vision system with custom hardware & GUI for depth and 3D point clouds in phenotyping. https://github.com/smiler488/Stereo-Vision-Camera-Box
• CCO-Flight-Planner · Python, UAV Technology Automated DJI flight planning from KML polygons; KMZ waypoint generation for field surveys. https://github.com/smiler488/cco-flight-planner
• RootQuantify · Python, Image Analysis Batch root-image quantification with robust preprocessing and morphology metrics. https://github.com/smiler488/RootQuantify
• Custom-Harvard-Citation-Tool · Academic Productivity Zotero-friendly citation insertion with journal-abbreviation support (slides/papers). https://github.com/smiler488/custom-harvard-with-journal-abbr

Technical Impact: 50+ combined stars; adopted in practical ag-research workflows.

Languages​

• Chinese (Mandarin): Native
• English: Proficient (academic writing, presentations, collaboration)

References​

Prof. Yali Zhang Professor & Ph.D. Supervisor, College of Agriculture, Shihezi University Email: zhangyali_cn@foxmail.com

Dr. Qingfeng Song Research Associate & Co-supervisor, CAS Center for Excellence in Molecular Plant Sciences (CEMPS) Email: songqf@cemps.ac.cn

Additional references available upon request

Last updated: October 2025