Remote physiological monitoring of the giant panda and red panda using near infrared spectroscopy and machine learning

Aug 5, 2026

Appropriate conservation decisions require real-time, accurate information on wildlife populations, yet direct observation and capture are difficult for many threatened and secretive species. This dissertation evaluates whether near infrared spectroscopy (NIRS) can serve as a remote analytical tool by detecting animal “signs” without seeing or capturing animals. Using giant pandas and red pandas as case studies, it tests NIRS combined with mode-cloning and machine learning for nutritional foodscape and demographic analysis, including calibration transfer to field conditions and prediction of reproductive status from minimally processed fecal and forage samples.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages206

Reading Time8 h 39 min

AccessFree to download

Hypotheses and Objectives

Mode-cloning and calibration transfer approach

Machine learning classification tasks

Research Findings and Implications

Real-time monitoring potential

Decision support for in situ and ex situ efforts

Mississippi State University Scholars Junction | Theses and Dissertations | Theses and Dissertations | | --- | --- | | 5-12-2023
Remote physiological monitoring of the giant panda and red panda using near infrared spectroscopy and machine learning
Qingyu Sheng
Mississippi State University, [qingyusheng00@gmail.com](qingyusheng00@gmail.com)
Follow this and additional works at: [https://scholarsjunction.msstate.edu/td](https://scholarsjunction.msstate.edu/td)
Part of the Other Animal Sciences Commons, Other Physiology Commons, and the Zoology Commons | | Recommended Citation Sheng, Qingyu, "Remote physiological monitoring of the giant panda and red panda using near infrared spectroscopy and machine learning" (2023) . Theses and Dissertations. 5821. [https://scholarsjunction.msstate.edu/td/5821](https://scholarsjunction.msstate.edu/td/5821) This Dissertation-Open Access is brought to you for free and open access by the Theses and Dissertations at Scholars Junction. It has been accepted for inclusion in Theses and Dissertations by an authorized administrator of Scholars Junction. For more information, please contact scholcomm@msstate. libanswers.com. Remote physiological monitoring of the giant panda and red panda using near infrared spectroscopy and machine learning By Qingyu Sheng Approved by: Carrie Kim Vance (Major Professor/Graduate Coordinator) Andrew J. Kouba Guiming Wang Ashli E. Brown Scott T. Willard (Dean, College of Agriculture and Life Sciences) A Dissertation Submitted to the Faculty of Mississippi State University in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy in Life Sciences (Animal Physiology) in the Department of Biochemistry, Molecular Biology, Entomology & Plant Pathology Mississippi State, Mississippi May 2023 Copyright by Qingyu Sheng 2023 Name: Qingyu Sheng Date of Degree: May 12, 2023 Institution: Mississippi State University Major Field: Life Sciences (Animal Physiology) Major Professor: Carrie Kim Vance Title of Study: Remote physiological monitoring of the giant panda and red panda using near infrared spectroscopy and machine learning Pages in Study: 192 Candidate for Degree of Doctor of Philosophy Appropriate conservation decisions and efforts must be based on real−time and accurate information about wildlife populations. However, it is extremely challenging to monitor the population demography and physiological traits of many threatened and secretive animal species through direct observation and capture. Near infrared spectroscopy (NIRS) has the potential to bea remote tool to address questions concerning wildlife physiology and demography by analyzing“signs” of animals without seeing or capturing them. In this dissertation, two species, the giant panda (Ailuropoda melanoleuca) and red panda (Ailurus fulgens) are used as a case study, to demonstrate NIRS’ feasibility in studying their physiological properties. The aim of this study is to test NIRS’ potential as a real−time analytical tool for in the nutritional foodscape and demographic analysis using less processed or non−processed field fecal and forage samples with the help of the mode−cloning technique to transfer the master model (dry and ground samples) under laboratory conditions to satellite modes (wet or dry but unground) in field conditions. Mode−cloning is conducted using either slope and bias correction (SBC) or two spectral correction methods, piecewise direct standardization (PDS) and external parameter orthogonalization (EPO) . The following four hypotheses are tested this dissertation: (1) by using mode−cloning with both SBC and PDS, unprocessed wet or unground dry bamboo leaves (pandas’ food) can be used to determine the crude protein contents; (2) machine learning−based classification models using less processed field feces after mode−cloning with spectral correction approaches (PDS and EPO) can differentiate betw

FAQs

Why is real-time physiological monitoring important for wildlife conservation?

Accurate conservation decisions depend on real-time information about wildlife populations, but direct monitoring of demography and physiology is difficult for many threatened and secretive species.

How does near infrared spectroscopy (NIRS) support remote monitoring in this dissertation?

NIRS is explored as a remote tool that can analyze animal “signs” without requiring direct observation or capture, using minimally processed biological samples.

What does “mode-cloning” enable in this study?

Mode-cloning transfers a master model from laboratory conditions (dry and ground samples) to satellite modes representing field conditions (wet or dry but unground), using spectral correction methods to support analysis in situ.

Aug 5, 2026

Upload by Olivia Brown