Abstract
At the present stage, the effective coupling information of “ground-space” is still a fundamental way to detect forest pest damage rapidly and accurately in remote sensing. It is of great significance to explore and construct a detection model that can comprehensively and effectively utilize ground microscopic features and remote sensing pixel information. Taking Dendrolimus punctatus Walker damage as the study object, the host characteristics and the differences with healthy pine forest are analyzed from the aspects of leaf volume, greenness, moisture, forest form and spectrum. Four experimental sites of Sanming City, Jiangle County, Sha County and Yanping District in Nanping City, Fujian, China are set as the experimental areas, and two forest stand features of LAI and SEL are measured, the remote sensing indicators of NDVI, WET and B2, B3, B4 are calculated or extracted. The PCA-RF detection model is constructed with pest levels of non-damage, mild damage, moderate damage and severe damage as dependent variables. This model reduces the dimensions by converting the initial variables into several principal components and making the principal components input to the random forest. The first three principal components of PCA can better replace the information of the original seven characteristic indicators, thereby reducing the seven-dimensional information to three dimensions. One hundred eighty-two samples are randomly divided into the training set and test set for the five repeats. The detection accuracy, Kappa coefficient, ROC are selected to evaluate the pest damage detection effects of PCA-RF model, and compare with Fisher discriminant analysis and BP neural network. The results show that the detection accuracy, Kappa coefficient and AUC of PCA-RF model in the training set are not as good as those of FDA and BPNN, but the detection accuracy and Kappa coefficient in the test set are significantly better than the other two algorithms, and the AUC value is also significantly higher than BNPP. This study proves that PCA-RF model simplifies the complex problem, inherits the advantages of random forest, has very strong generalization ability and robustness, and can be used as an effective solution for forest pest and disease detection.
Similar content being viewed by others
References
Adelabu S, Mutanga O, Adam E (2014) Evaluating the impact of red-edge band from Rapideye image for classifying insect defoliation levels. ISPRS J Photogr Remote Sens 95:34–41
Bernard S, Heutte L, Adam S (2009) On the selection of decision trees in Random Forests. In: International joint conference on neural networks. IEEE, pp 302–307
Bone C, Dragicevic S, Roberts A (2006) A fuzzy-constrained cellular automata model of forest insect infestations. Ecol Model 192:107–125
Breiman L (2001) Random forest. Mach Learn 45:5–32
Chen WT, Li XJ, Wang YX, Chen G, Liu SW (2014) Forested landslide detection using LiDAR data and the random forest algorithm: a case study of the three gorges, China. Remote Sens Environ 152:291–301
Clark KL, Skowronski N, Hom J (2010) Invasive insects impact forest carbon dynamics. Glob Change Biol 16:88–101
Das N (2014) Allometric modeling for leaf area and leaf biomass estimation of Swietenia mahagoni in the north-eastern region of Bangladesh. J For Sci 30:351–361
Dash JP, Watt MS, Pearse GD, Heaphy M, Dungey HS (2017) Assessing very high resolution UAV imagery for monitoring forest health during a simulated disease outbreak. ISPRS Int J Photogr Remote Sens 131:1–14
Fang KN, Wu JB, Zhu JP, Xie BC (2011) A review of technologies on random forests. Stat Inf Forum 26:32–38
Feng LJ (2007) Study on the dynamic monitoring system over forest pest in Xianning. Central South University of Forestry and Technology
Feng Q, Liu J, Gong J (2015) UAV remote sensing for urban vegetation mapping using random forest and texture analysis. Remote Sens 7:1074–1094
Hall RJ, Fernandes RA, Hogg EH, Brandt JP, Butson C, Case BS, Leblanc SG (2003) Relating aspen defoliation to changes in leaf area derived from field and satellite remote sensing data. Can J Remote Sens 29:299–313
Houborg R, Mccabe MF (2017) A hybrid training approach for leaf area index estimation via Cubist and random forests machine-learning. ISPRS J Photogr Remote Sens 135:173–188
Huang WJ, Zhang JC, Shi Y, Dong YY, Liu LY (2018) Progress in monitoring and forecasting of crop pests and diseases by remote sensing. J Nanjing Univ Inf Eng (Nat Sci Edn) 10:30–43 ((in Chinese))
Jepsen JU, Hagen SB, Høgda KA, Ims RA, Karlsen SR, Tømmervik H, Yoccoz NG (2009) Monitoring the spatio-temporal dynamics of geometrid moth outbreaks in birch forest using MODIS-NDVI data. Remote Sens Environ 113:1939–1947
Lange H, Solberg S (2008) Leaf area index estimation using Lidar and forest reflectance modelling of airborne hyperspectral data. In: Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International. IEEE, pp 475–478
Li L, Mou SM, Lin ZQ (2017) Application of random forest in forecasting cotton aphid pest grade. Anhui Agric Sci Bull 23:18–20
Li MY, Liu ML, Liu M, Ju YW (2010) Prediction of pine wilt disease in Jiangsu Province based on web dataset and GIS. Web information systems and mining. Springer, Berlin, pp 146–153
Li XW, Wang YT (2013) Prospects on future developments of quantitative remote sensing. Acta Geogr Sin 68:1163–1169
Liu Q, Li XB, Liang WZ (2018) PCA-RF model for the classification of rock mass quality and its application. Gold Sci Technol 26:49–55
Luo SZ, Wang C (2001) Forest pests and diseases forecasting based on GIS. Adv Mater Res 250–253:2945–2948
Meng R, Dennison PE, Zhao F, Shendryk I, Rickert A, Hanavan RP, Cook BD, Serbin SP (2018) Mapping canopy defoliation by herbivorous insects at the individual tree level using bi-temporal airborne imaging spectroscopy and lidar measurements. Remote Sens Environ 215:170–183
Oszlányi J (1999) Leaf area index as the indicator of health state of forest within reach of the Gabcikovo hydropower plant. Ekologia Bratislava 18:173–178
Park YS, Chung YJ (2006) Hazard rating of pine trees from a forest insect pest using artificial neural networks. For Ecol Manag 222:222–233
Provost F, Hibert C, Malet JP (2017) Automatic classification of endogenous landslide seismicity using the Random Forest supervised classifier. Geophys Res Lett 44:1–8
Qian GJ, Zhang SP, Song XY, Bi SD, Zhang GQ, Zou YD, Fang GF, Yan P (2020) Forecast for the occurrence period of Dendrolimus punctatus larvae based on Bayes discriminant method for the first and second generations. Plant Protect 46(122–128):163
Rodriguez-Galiano VF, Ghimire B, Rogan J, Chica-Olmo M, Rigol-Sanchez JP (2012) An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS J Photogr Remote Sens 67:93–104
Rouse JW, Haas RH, Schell JA, Deering DW (1973) Monitoring vegetation systems in the Great Plains with ERTS. In: Proceedings of the third earth resources technology satellite-1 symposium, Greenbelt: NASA SP-351, pp 301–317
Rullansilva CD, Olthoff AE, de la Delgado MJA, Pajaresalonso JA (2013) Remote monitoring of forest insect defoliation. A Rev For Syst 22:377–391
Svetnik V, Liaw A, Tong C, Culberson JC, Sheridan RP, Feuston BP (2003) Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci 43:1947–1958
Valentine HT, Newton CM, Talerico RL (1976) Compatible systems and decision models for pest management. Environ Entomol 5:891–900
Wang L (2009) Remote sensing monitoring of insect pests in larch forest based on physical model. In: 2010 IEEE international geoscience and remote sensing symposium. Beijing Forestry University, Beijing
Wang L, Huang H, Luo Y (2010) Remote sensing of insect pests in larch forest based on physical model. In: Geoscience and remote sensing symposium. IEEE, pp 3299–3302
Wang Q, Adiku S, Tenhunen J, Granier A (2005) On the relationship of NDVI with leaf area index in a deciduous forest site. Remote Sens Environ 94:244–255
Wen AM, Zheng JH, Chen M, Mu C, Tao M (2016) Spatial distribution of rodent pests in desert forest based on UAV remote sensing. In: Geoscience and remote sensing symposium. IEEE, pp 1804–1807
Xie QY, Dash J, Huang WJ, Peng DL, Qin QM, Mortimer H, Casa R, Pignatti S, Laneve G, Pascucci S, Dong YY, Ye HC (2018) Vegetation indices combining the red and red-edge spectral information for leaf area index retrieval. IEEE J Select Top Appl Earth Observ Remote Sens 99:1–12
Xu GY, Xu W, Fang SA, Zhang J (2008) The Relationship between the occurring damage of Dendrolimus punctatus Walker and forest form. J Hebei Agric Sci 12:31–32
Xu ZH (2013) Space-based monitoring and early warning technologies of Dendrolimus punctatus Walker damage. Fujian Agricultural and Forestry University
Xu ZH, Huang XY, Lin L, Wang QF, Liu J, Chen CC, Yu KY, Zhou HK, Zhang HF (2018) Dendrolimus punctatus Walker damage detection based on Fisher discriminant analysis and random forest. Spectrosc Spectr Anal 38:2888–2896
Xu ZH, Li CH, Liu J, Yu KY, Gong CH, Tang MY (2014) Fisher discriminant analysis of Dendrolimus punctatus Walker pest levels. Trans Chin Soc Agric Mach 45:275–283
Xu ZH, Liu J, Yu KY, Gong CH, Xie WJ, Tang MY, Lai RW, Li ZL (2013) Leaf area index and standard error of pine forests estimated with common digital camera. Chin J Eco-Agric 21:638–644
You WB, You HM, Wu LY, Ji ZR, He DJ (2020) Landscape-level spatiotemporal patterns of Dendrolimus punctatus Walker and its driving forces: evidence from a Pinus massoniana forest. Trees 34:553–562
Yuan Y, Hu XY (2016) Random forest and objected-based classification for forest pest extraction from UAV aerial imagery. ISPRS—Int Arc Photogr Remote Sens Spatial Inf Sci XLI-B1:1093–1098
Zhu ZJ, Zhang HW, Chen Y (2015) Stability prediction of gateway surrounding rocks based on PCA-RF. Hydrogeol Eng Geol 42:108–113
Acknowledgements
This study was supported by the National Natural Science Foundation of China (42071300), the Fujian Provincial Natural Science Foundation (2020J01504), the China Postdoctoral Science Foundation (2018M630728), the National Natural Science Foundation of China (41501361; 30871965), the Open Fund of University Key Lab for Geomatics Technology and Optimize Resources Utilization in Fujian Province (fafugeo201901), the National Students’ Innovation and Entrepreneurship Training Program (201710386020), Fujian Provincial Students’ Innovation and Entrepreneurship Training Program (201810386101), the Open Fund of Fujian Provincial Key Laboratory of Resources and Environment Monitoring and Sustainable Management and Utilization (ZD1403), the Open Fund of Fujian Mine Ecological Restoration Engineering Technology Research Center (KS2018005) and the Scientific Research Foundation of Fuzhou University (XRC1345).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xu, Z., Shi, W., Lin, L. et al. PCA-RF model for Dendrolimus punctatus Walker damage detection. Nat Hazards 106, 991–1009 (2021). https://doi.org/10.1007/s11069-021-04503-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11069-021-04503-4