Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jianhua Ma has a total of 41 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Vision-Based AI Framework for Person and Vehicle Detection with Risk-Level Classification in Flood Disaster Scenarios

    by Jianhua Ma, Yongzhang Zhou, Lu-Hao He, Yichao Zhao, Guoqing Liu

    Flood disasters are characterized by rapid onset, extensive spatial impact, and highly complex scene conditions. Rapid identification of exposed persons and vehicles, together with an assessment of their risk states, is essential for improving flood emergency situational awareness and supporting timely response decisions. However, existing visual object detection studies mainly focus on generic object category recognition and provide limited capability for representing inundation-related exposure states in flood environments. To address this limitation, this study proposes a vision-based artificial intelligence framework for person and vehicle detection with risk-level classification in flood disaster scenarios. The AI contribution of this work lies in reformulating conventional object detection as a flood-context-aware, fine-grained risk perception task through a six-subclass annotation scheme and a YOLOv26-based detection framework. The engineering application lies in providing actionable visual information for identifying exposed elements and supporting emergency response in complex flood-affected environments.A flood-specific image dataset was constructed from publicly available online sources, covering representative scenarios such as urban waterlogging, road inundation, residential flooding, and emergency rescue operations. Persons and vehicles were treated as two key types of exposed elements, and each was further divided into three risk levels according to visible inundation conditions, resulting in six fine-grained risk-level subclasses. YOLOv26 was adopted as the base detection framework to exploit its end-to-end detection mechanism, multi-scale feature fusion capability, and adaptability to complex visual scenes.

  • Open Access

    High-Resolution UAV Monitoring of Floating Aquatic Vegetation in Complex Surface Water Environments Using Deep Learning

    by Lu-Hao He, Yongzhang Zhou, Xian Liu, Jianhua Ma, Jingjing Feng, Dianxian Lai

    Floating aquatic vegetation is a dynamic component of surface water environments and may influence open-water availability, water–land connectivity and routine water-environment management when excessive proliferation occurs. High-resolution monitoring of floating vegetation is therefore important for identifying spatially heterogeneous plant coverage in rivers, lakes, drainage channels and riparian water bodies. However, automated detection from unmanned aerial vehicle (UAV) imagery remains challenging because floating plant patches often exhibit irregular boundaries, substantial scale variations and strong visual similarity to water-surface reflections, shadows, riparian vegetation, fixed wetland plants and other heterogeneous background features. These challenges limit the operational use of UAV imagery for rapid surface-water monitoring and management-oriented assessment.In this study, we developed a UAV-based deep learning framework for detecting floating aquatic vegetation in complex surface water environments. A dedicated UAV image dataset was constructed, and YOLOv26 was adopted as the baseline object detection model to evaluate training convergence, detection accuracy and representative error patterns. The training process exhibited stable convergence, with progressively decreasing loss functions and improved detection metrics. At the final training stage, the model achieved a precision of 0.7663, a recall of 0.7194 and an F1 score of 0.7421. The mean average precision at an IoU threshold of 0.5 reached 0.7617, while mAP50-95 reached 0.6699. The average detection confidence on the test set was 74.28%. These results indicate that the proposed framework can effectively identify and localize floating aquatic vegetation from UAV imagery under complex water-surface conditions.The model showed relatively strong responsiveness to large, contiguous and shoreline-distributed floating vegetation aggregations, suggesting its potential for rapid screening of vegetation-covered water surfaces. Nevertheless, representative error analysis revealed several limitations relevant to hydrological and water-environment monitoring. False-positive detections occurred where floating vegetation was visually connected with riparian vegetation, fixed wetland plants or wooded background features, while small and discretely distributed plant patches remained difficult to detect. These findings indicate that further improvements in water–land contextual discrimination, small-target representation and multi-scale feature learning are required before the method can be used for more precise water-surface coverage estimation.Overall, this study demonstrates the feasibility of integrating UAV imagery and deep learning object detection for high-resolution monitoring of floating aquatic vegetation in complex surface water environments. The proposed approach provides a practical technical basis for rapid identification of vegetation-affected water-surface areas and may support surface-water observation, riparian water-environment management and future catchment-scale monitoring workflows when combined with multi-temporal UAV surveys and hydrological context information.

  • Open Access

    Mini-CarbonGPT: A Resource-Efficient Knowledge-Augmented Framework for Environmental Decision Support in Carbon Neutrality Engineering

    by Jianhua Ma, Xian Liu, Yongzhang Zhou, Luhao He, Yijun Zheng

    Carbon neutrality engineering requires integrating heterogeneous knowledge from technical literature, standards, policy documents, and carbon accounting rules. General-purpose large language models often lack domain alignment and factual reliability in such knowledge-intensive settings. This study presents Mini-CarbonGPT, a resource-efficient knowledge-augmented framework for environmental decision support in carbon neutrality engineering. Built on GLM-4-9B, it combines parameter-efficient fine-tuning (LoRA) with retrieval-augmented generation (RAG) to support lightweight domain adaptation and evidence-grounded response generation. The framework was developed using 50,000 general instructions, 5,382 domain-specific instructions, 6,096 research articles, and about 60,000 curated Wikipedia entries, and evaluated on a benchmark of 700 objective and 249 open-ended questions. Mini-CarbonGPT achieved 80.57% average objective accuracy, outperforming the base model and showing competitive performance against several commercial LLMs. The study provides a reproducible and transferable framework for AI-enhanced environmental knowledge integration and decision support.

  • Open Access

    Mini-CarbonGPT: A Resource-Efficient Knowledge-Augmented Language Model for Industrial Decarbonization Knowledge Work

    by Jianhua Ma, Yongzhang Zhou, Xian Liu, Lu-Hao He, Yijun Zheng

    Industrial decarbonization involves knowledge-intensive tasks that require engineers and practitioners to access, interpret, and integrate heterogeneous information from technical literature, policy documents, standards, and domain reports. General-purpose large language models often struggle in this setting because of limited domain alignment and weak factual grounding. This study presents Mini-CarbonGPT, a resource-efficient domain language model for industrial decarbonization knowledge work. The system combines parameter-efficient fine-tuning using Low-Rank Adaptation (LoRA) with retrieval-augmented generation (RAG) to couple domain adaptation with evidence-grounded response generation under limited computational resources. A multi-source knowledge pipeline was constructed using 50,000 general instructions, 5,382 domain-specific instructions, 6,096 research papers, and approximately 60,000 curated encyclopedia entries. To evaluate performance in engineering-oriented knowledge tasks, we developed a benchmark containing 700 objective questions and 249 open-ended questions across five carbon-neutrality subdomains. Results show that Mini-CarbonGPT achieved an average objective accuracy of 80.57%, outperforming the baseline model and showing robust performance in factual accuracy, terminology coverage, and response completeness. The proposed framework demonstrates how lightweight adaptation and external knowledge retrieval can be integrated to support industrial knowledge services in complex engineering domains. The study provides a transferable approach for building domain language models for industrial applications where knowledge reliability, deployability, and reproducibility are critical.

  • Open Access

    Mini-CarbonGPT: A Domain-Adapted Large Language Model for Engineering Knowledge Integration and Decision Support

    by Jianhua Ma, Yongzhang Zhou, Xian Liu, Lu-Hao He, Yijun Zheng, Lu Su, Huanrong Yang

    Engineering decision-making in complex, interdisciplinary domains is increasingly challenged by fragmented knowledge sources, heterogeneous data representations, and rapidly evolving technical standards. Large language models (LLMs) offer new opportunities for semantic integration and AI-assisted reasoning; however, general-purpose models often lack domain alignment and factual reliability in professional engineering contexts. This study proposes Mini-CarbonGPT, a domain-adapted large language model designed for engineering knowledge integration and decision support. Built upon the GLM-4-9B architecture, Mini-CarbonGPT adopts a dual-path adaptation strategy that combines parameter-efficient fine-tuning (LoRA) with retrieval-augmented generation (RAG) to enable effective domain specialization under limited computational resources. A multi-source engineering knowledge corpus is constructed, including 50,000 general instructions, 5,382 domain-specific instructions, 6,096 research articles, and approximately 60,000 curated Wikipedia entries. To systematically evaluate engineering-oriented reasoning and knowledge reliability, we develop a comprehensive benchmark consisting of 700 objective questions and 249 open-ended questions across multiple subdomains. Experimental results demonstrate that Mini-CarbonGPT achieves an average objective accuracy of 80.57% and exhibits competitive performance in factual correctness, reasoning completeness, and domain terminology coverage compared with both the base model and mainstream commercial LLMs. Using carbon neutrality engineering as a representative application scenario, Mini-CarbonGPT supports tasks such as emission factor interpretation, pathway comparison, and policy-oriented analysis. The proposed knowledge integration pipeline and adaptation methodology provide a reproducible and transferable framework for developing domain-specific engineering language models and AI-driven decision-support systems in complex engineering domains.

  • Open Access

    Enhancing Geological Knowledge Engineering with Retrieval-Augmented Generation: A Case Study of the Qin–Hang Metallogenic Belt

    by Jianhua Ma, Yongzhang Zhou, Luhao He, Qianlong Zhang, Muhammad Atif Bilal, Yuqing Zhang

    This study presents a domain-adapted retrieval-augmented generation (RAG) pipeline that integrates geological knowledge with large language models (LLMs) to support intelligent question answering in the metallogenic domain. Focusing on the Qin–Hang metallogenic belt in South China, we construct a bilingual question-answering (QA) corpus derived from 615 authoritative geological publications, covering topics such as regional tectonics, ore-forming processes, structural evolution, and mineral resources. Using the ChatGLM3-6B language model and LangChain framework, we embed the corpus into a semantic vector database via Sentence-BERT and FAISS, enabling dynamic retrieval and grounded response generation. The RAG-enhanced model significantly outperforms baseline LLMs—including ChatGPT-4, Bing, and Gemini—in a comparative evaluation using BLEU, precision, recall, and F1 metrics, achieving an F1 score of 0.8689. The approach demonstrates high domain adaptability and reproducibility. All datasets and codes are openly released to facilitate application in other metallogenic belts. This work illustrates the potential of LLM-based knowledge engineering to support digital geoscientific research and smart mining.


  • Open Access

    A Systematic Review of Carbon Sink Pathways and Deployment Strategies

    by Jianhua Ma, Yongzhang Zhou, Luhao He

    Amid the global dual transformation toward deep decarbonization and net-zero emissions, carbon sequestration pathways have become indispensable pillars of climate governance. Natural sinks and engineered carbon removal approaches exhibit high heterogeneity in sequestration mechanisms, temporal effectiveness, environmental externalities and societal acceptance. Yet, current research lacks an integrated understanding of cross-pathway synergies, spatial deployment logics and dynamic scheduling strategies, calling for a more systemic and adaptive framework. This review provides a comprehensive synthesis of the carbon storage structure and regulatory drivers of terrestrial (forests, wetlands) and marine sinks, assessing their spatial potential and ecological coupling. It also critically evaluates the technological readiness, sequestration stability and deployment thresholds of engineered options such as BECCS, DAC, enhanced weathering and ocean alkalinization. Key divergences between natural and artificial pathways are highlighted in terms of carbon removal capacity, energy intensity, deployment timing and governance risk. We identify persistent bottlenecks, including the absence of synergistic deployment models, resource and institutional constraints at the regional scale, unquantified system feedbacks and limitations in monitoring, reporting and verification (MRV) mechanisms. These issues inhibit the scale-up and long-term stability of carbon sink systems. To address these challenges, we propose a Pathway-Region-Temporal (P-R-T) scheduling model that integrates technological characteristics, spatial suitability and sequencing dynamics into a unified optimization framework. We further advance a “Carbon Flow-Storage-Feedback Loop” architecture to guide the adaptive evolution of carbon sink systems under uncertainty, enabling coordinated deployment, real-time optimization and policy responsiveness. We argue for a strategic shift from fragmented pathway management toward systemic carbon sink engineering, integrating multi-path coordination, dynamic feedback recognition, scalable infrastructure and robust MRV systems. Such an approach lays the scientific foundation for achieving high-resilience, low-risk net-zero trajectories in global carbon governance.