Enhancing forest insect outbreak detection by integrating tree-ring and climate variables

doi:10.1007/s11676-024-01759-x

Abstract

Abstract:

Annual tree rings are widely recognized as valuable tools for quantifying and reconstructing historical forest disturbances. However, the influence of climate can complicate the detection of disturbance signals, leading to limited accuracy in existing methods. In this study, we propose a random under-sampling boosting (RUB) classifier that integrates both tree-ring and climate variables to enhance the detection of forest insect outbreaks. The study focused on 32 sites in Alberta, Canada, which documented insect outbreaks from 1939 to 2010. Through thorough feature engineering, model development, and tenfold cross-validation, multiple machine learning (ML) models were constructed. These models used ring width indices (RWIs) and climate variables within an 11-year window as input features, with outbreak and non-outbreak occurrences as the corresponding output variables. Our results reveal that the RUB model consistently demonstrated superior overall performance and stability, with an accuracy of 88.1%, which surpassed that of the other ML models. In addition, the relative importance of the feature variables followed the order RWIs > mean maximum temperature (T _max) from May to July > mean total precipitation (P _mean) in July > mean minimum temperature (T _min) in October. More importantly, the dfoliatR (an R package for detecting insect defoliation) and curve intervention detection methods were inferior to the RUB model. Our findings underscore that integrating tree-ring width and climate variables as predictors in machine learning offers a promising avenue for enhancing the accuracy of detecting forest insect outbreaks.

Key words: Forest disturbance, Insect outbreaks, Machine learning, Tree-ring analysis

Yao Jiang, Zhou Wang, Zhongrui Zhang, Xiaogang Ding, Shaowei Jiang, Jianguo Huang. Enhancing forest insect outbreak detection by integrating tree-ring and climate variables[J]. JOURNAL OF FORESTRY RESEARCH, 2024, 35(1): 106-.

Yao Jiang, Zhou Wang, Zhongrui Zhang, Xiaogang Ding, Shaowei Jiang, Jianguo Huang. [J]. 林业研究(英文版), 2024, 35(1): 106-.

References 70

1	Ahmed I, Yadav PK. Plant disease detection using machine learning approaches. Expert Syst, 2023, 40(5): , DOI
2	Allen CD, Macalady AK, Chenchouni H, Bachelet D, McDowell N, Vennetier M, Kitzberger T, Rigling A, Breshears DD, Hogg EH, Gonzalez P, Fensham R, Zhang Z, Castro J, Demidova N, Lim JH, Allard G, Running SW, Semerci A, Cobb N. A global overview of drought and heat-induced tree mortality reveals emerging climate change risks for forests. For Ecol Manag, 2010, 259(4): 660-684, DOI
3	Anderson-Teixeira KJ, Herrmann V, Rollinson CR, Gonzalez B, Gonzalez-Akre EB, Pederson N, Alexander MR, Allen CD, Alfaro-Sánchez R, Awada T, Baltzer JL, Baker PJ, Birch JD, Bunyavejchewin S, Cherubini P, Davies SJ, Dow C, Helcoski R, Kašpar J, Lutz JA, Margolis EQ, Maxwell JT, McMahon SM, Piponiot C, Russo SE, Šamonil P, Sniderhan AE, Tepley AJ, Vašíčková I, Vlam M, Zuidema PA. Joint effects of climate, tree size, and year on annual tree growth derived from tree-ring records of ten globally distributed forests. Glob Chang Biol, 2022, 28(1): 245-266, DOI
4	Aryal S, Grießinger J, Arsalani M, Meier WJH, Fu PL, Fan ZX, Bräuning A. Insect infestations have an impact on the quality of climate reconstructions using Larix ring-width chronologies from the Tibetan Plateau. Ecol Indic, 2023, 148, DOI
5	Bai BX, Tan YM, Donchyts G, Haag A, Xu B, Chen G, Weerts AH. Naive Bayes classification-based surface water gap-filling from partially contaminated optical remote sensing image. J Hydrol, 2023, 616, DOI
6	Birkes DS, Seely JF, Vanleeuwen DM. Balance and orthogonality in designs for mixed classification models. Ann Stat, 1999, 27(6): 1927-1947, DOI
7	Björklund J, Rydval M, Schurman JS, Seftigen K, Trotsiuk V, Janda P, Mikoláš M, Dušátko M, Čada V, Bače R, Svoboda M. Disentangling the multi-faceted growth patterns of primary Picea abies forests in the Carpathian arc. Agric For Meteorol, 2019, 271: 214-224, DOI
8	Black BA, Abrams MD. Development and application of boundary-line release criteria. Dendrochronologia, 2004, 22(1): 31-42, DOI
9	Bond-Lamberty B, Rocha AV, Calvin K, Holmes B, Wang CK, Goulden ML. Disturbance legacies and climate jointly drive tree growth and mortality in an intensively studied boreal forest. Glob Chang Biol, 2014, 20(1): 216-227, DOI
10	Bunn AG. A dendrochronology program library in R (dplR). Dendrochronologia, 2008, 26(2): 115-124, DOI
11	Burez J, Van den Poel D. Handling class imbalance in customer churn prediction. Expert Syst Appl, 2009, 36(3): 4626-4636, DOI
12	Chapin FS, Starfield AM. Time lags and novel ecosystems in response to transient climatic change in Arctic Alaska. Clim Change, 1997, 35(4): 449-461, DOI
13	Chen H, Hu SH, Hua R, Zhao XJ. Improved naive Bayes classification algorithm for traffic risk management. EURASIP J Adv Signal Process, 2021, 2021(1): 30, DOI
14	Chen L, Huang JG, Alam SA, Zhai LH, Dawson A, Stadt KJ, Comeau PG. Drought causes reduced growth of trembling aspen in western Canada. Glob Chang Biol, 2017, 23(7): 2887-2902, DOI
15	Chen W, Xie XS, Wang JL, Pradhan B, Hong HY, Bui DT, Duan Z, Ma JQ. A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility. CATENA, 2017, 151: 147-160, DOI
16	Cook ER. The decomposition of tree-ring series for environmental studies. Tree Ring Res, 1987, 47: 37-59
17	Cook ER, Kairiukstis LA. Methods of dendrochronology: applications in the environmental sciences, 1990 Boston Kluwer Academic Publishers, DOI
18	da Penha PA, da Silva Junior JA, Ruiz-Armenteros AM, Henriques RFF. Assessment of k-nearest neighbor and random forest classifiers for mapping forest fire areas in central Portugal using landsat-8, sentinel-2, and terra imagery. Remote Sens, 2021, 13(7): 1345, DOI
19	Ding D, Jia WX, Ma XG, Wang J. Water source of dominant plants of the subalpine shrubland in the Qilian Mountains, China. Acta Ecol Sinica, 2018, 38: 1348-1356, DOI
20	Drobyshev I, Gewehr S, Berninger F, Bergeron Y. Species specific growth responses of black spruce and trembling aspen may enhance resilience of boreal forest to climate change. J Ecol, 2013, 101(1): 231-242, DOI
21	Druckenbrod DL. Dendroecological reconstructions of forest disturbance history using time-series analysis with intervention detection. Can J For Res, 2005, 35(4): 868-876, DOI
200	Emerson P (2013) The original Borda count and partial voting. Soc Choice Welfare 40(2):353–358
22	Feki-Sahnoun W, Njah H, Hamza A, Barraj N, Mahfoudi M, Rebai A, Hassen MB. Using general linear model, Bayesian networks and naive Bayes classifier for prediction of Karenia selliformis occurrences and blooms. Ecol Inform, 2018, 43: 12-23, DOI
23	Foster AC, Wang JA, Frost GV, Davidson SJ, Hoy E, Turner KW, Sonnentag O, Epstein H, Berner LT, Armstrong AH, Kang M, Rogers BM, Campbell E, Miner KR, Orndahl KM, Bourgeau-Chavez LL, Lutz DA, French N, Chen D, Du J, Shestakova TA, Shuman JK, Tape K, Virkkala AM, Potter C, Goetz S. Disturbances in North American boreal forest and Arctic tundra: impacts, interactions, and responses. Environ Res Lett, 2022, 17(11): , DOI
24	Fraver S, White AS. Identifying growth releases in dendrochronological studies of forest disturbance. Can J For Res, 2005, 35(7): 1648-1656, DOI
25	Gou XX, Zhang TW, Yu SL, Liu KX, Zhang RB, Shang HM, Qin L, Fan YT, Jiang SX, Zhang HL, Guo D. Climate response of Picea schrenkiana based on tree-ring width and maximum density. Dendrochronologia, 2023, 78, DOI
26	Guiterman CH, Lynch AM, Axelson JN. dfoliatR: an R package for detection and analysis of insect defoliation signals in tree rings. Dendrochronologia, 2020, 63, DOI
27	Guo K, Hao SG, Sun OJ, Kang L. Differential responses to warming and increased precipitation among three contrasting grasshopper species. Glob Change Biol, 2009, 15(10): 2539-2548, DOI
28	Harati S, Perez L, Molowny-Horas R. Integrating neighborhood effect and supervised machine learning techniques to model and simulate forest insect outbreaks in British Columbia, Canada. Forests, 2020, 11(11): 1215, DOI
29	Harvey JA, Heinen R, Gols R, Thakur MP. Climate change-mediated temperature extremes and insects: from outbreaks to breakdowns. Glob Chang Biol, 2020, 26(12): 6685-6701, DOI
30	He MH, Yang B, Wang ZY, Bräuning A, Pourtahmasi K, Oladi R. Climatic forcing of xylem formation in Qilian juniper on the northeastern Tibetan Plateau. Trees, 2016, 30(3): 923-933, DOI
31	Holmes RL. Computer-assisted quality control in tree-ring dating and measurement. Tree Ring Res, 1983, 44: 69-75, DOI
32	Hosseinalizadeh M, Kariminejad N, Chen W, Pourghasemi HR, Alinejad M, Mohammadian Behbahani A, Tiefenbacher JP. Gully headcut susceptibility modeling using functional trees, naïve Bayes tree, and random forest models. Geoderma, 2019, 342: 1-11, DOI
33	Hua FY, Bruijnzeel LA, Meli P, Martin PA, Zhang J, Nakagawa S, Miao XR, Wang WY, McEvoy C, Peña-Arancibia JL, Brancalion PHS, Smith P, Edwards DP, Balmford A. The biodiversity and ecosystem service contributions and trade-offs of forest restoration approaches. Science, 2022, 376(6595): 839-844, DOI
34	Huang JG, Tardif J, Denneler B, Bergeron Y, Berninger F. Tree-ring evidence extends the historic northern range limit of severe defoliation by insects in the aspen stands of western Quebec, Canada. Can J For Res, 2008, 38(9): 2535-2544, DOI
35	Hutchinson M. ANUSPLIN version 4.3. centre for resource and environmental studies, 2004 Canberra Australian National University
36	Jeni LA, Cohn JF, De La Torre F (2013) Facing imbalanced data—recommendations for the use of performance metrics. In: 2013 humaine association conference on affective computing and intelligent interaction, IEEE, Geneva, Switzerland, 245–251 https://doi.org/10.1109/acii.2013.47
37	Jiang YY, Zhang XQ, Zhang JG, Chhin S. Comparing the random forest algorithm with other modelling approaches to capture the complex patterns of intra-annual wood formation of Chinese fir with different ages. Dendrochronologia, 2023, 77, DOI
38	Jönsson AM, Pulatov B, Linderson ML, Hall K. Modelling as a tool for analysing the temperature-dependent future of the Colorado potato beetle in Europe. Glob Chang Biol, 2013, 19(4): 1043-1055, DOI
39	Kiefer MT, Andresen JA, McCullough DG, Baule WJ, Notaro M. Extreme minimum temperatures in the great lakes region of the United States: a climatology with implications for insect mortality. Int J Climatol, 2022, 42(7): 3596-3615, DOI
40	Kulakowski D, Seidl R, Holeksa J, Kuuluvainen T, Nagel TA, Panayotov M, Svoboda M, Thorn S, Vacchiano G, Whitlock C, Wohlgemuth T, Bebi P. A walk on the wild side: disturbance dynamics and the conservation and management of European Mountain forest ecosystems. For Ecol Manag, 2017, 388: 120-131, DOI
41	Kurz WA, Dymond CC, Stinson G, Rampley GJ, Neilson ET, Carroll AL, Ebata T, Safranyik L. Mountain pine beetle and forest carbon feedback to climate change. Nature, 2008, 452(7190): 987-990, DOI
42	Lu WZ, Xiao JF, Cui XW, Xu FH, Lin GX, Lin GH. Insect outbreaks have transient effects on carbon fluxes and vegetative growth but longer-term impacts on reproductive growth in a mangrove forest. Agric For Meteorol, 2019, 279, DOI
43	Maselli F, Chirici G, Bottai L, Corona P, Marchetti M. Estimation of mediterranean forest attributes by the application of k-NN procedures to multitemporal landsat ETM+ images. Int J Remote Sens, 2005, 26(17): 3781-3796, DOI
44	Melgani F, Bruzzone L. Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans Geosci Remote Sens, 2004, 42(8): 1778-1790, DOI
45	Nelson WA, Bjørnstad ON, Yamanaka T. Recurrent insect outbreaks caused by temperature-driven changes in system stability. Science, 2013, 341(6147): 796-799, DOI
46	Nowacki GJ, Abrams MD. Radial-growth averaging criteria for reconstruction disturbance histories from presettlement-origin oaks. Ecol Monogr, 1997, 67(2): 225, DOI
47	Qin YP, Wu BY, Lei XD, Feng LY. Prediction of tree crown width in natural mixed forests using deep learning algorithm. For Ecosyst, 2023, 10, DOI
48	Ramazi P, Kunegel-Lion M, Greiner R, Lewis MA. Predicting insect outbreaks using machine learning: a mountain pine beetle case study. Ecol Evol, 2021, 11(19): 13014-13028, DOI
49	Rydval M, Druckenbrod D, Anchukaitis KJ, Wilson R. Detection and removal of disturbance trends in tree-ring series for dendroclimatology. Can J For Res, 2016, 46(3): 387-401, DOI
50	Rydval M, Druckenbrod DL, Svoboda M, Trotsiuk V, Janda P, Mikoláš M, Čada V, Bače R, Teodosiu M, Wilson R. Influence of sampling and disturbance history on climatic sensitivity of temperature-limited conifers. Holocene, 2018, 28(10): 1574-1587, DOI
51	Ryerson DE, Swetnam TW, Lynch AM. A tree-ring reconstruction of western spruce budworm outbreaks in the San Juan Mountains, Colorado, U.S.A. Can J For Res, 2003, 33(6): 1010-1028, DOI
52	Santi E, Clarizia MP, Comite D, Dente L, Guerriero L, Pierdicca N. Detecting fire disturbances in forests by using GNSS reflectometry and machine learning: a case study in Angola. Remote Sens Environ, 2022, 270, DOI
53	Senf C, Campbell EM, Pflugmacher D, Wulder MA, Hostert P. A multi-scale analysis of western spruce budworm outbreak dynamics. Landsc Ecol, 2017, 32(3): 501-514, DOI
54	Siliņš I, Kārkliņa A, Miezīte O, Jansons Ā. Trends in outbreaks of defoliating insects highlight growing threats for central European forests, and implications for eastern Baltic Region. Forests, 2021, 12(6): 799, DOI
55	Soleymani R, Granger E, Fumera G. Progressive boosting for class imbalance and its application to face re-identification. Expert Syst Appl, 2018, 101: 271-291, DOI
56	Speer JH, Swetnam TW, Wickman BE, Youngblood A. Changes in Pandora moth outbreak dynamics during the past 622 years. Ecology, 2001, 82(3): 679, DOI
57	Stephens JJ, Black TA, Jassal RS, Nesic Z, Grant NJ, Barr AG, Helgason WD, Richardson AD, Johnson MS, Christen A. Effects of forest tent caterpillar defoliation on carbon and water fluxes in a boreal aspen stand. Agric For Meteorol, 2018, 253: 176-189, DOI
58	Stevens-Rumann CS, Kemp KB, Higuera PE, Harvey BJ, Rother MT, Donato DC, Morgan P, Veblen TT. Evidence for declining forest resilience to wildfires under climate change. Ecol Lett, 2018, 21(2): 243-252, DOI
59	Stokes MA, Smiley TL. An introduction to tree-ting dating, 1996 Tucson University of Arizona Press
60	Suominen L, Ruokolainen K, Tuomisto H, Llerena N, Higgins MA. Predicting soil properties from floristic composition in western Amazonian rain forests: performance of k-nearest neighbour estimation and weighted averaging calibration. J Appl Ecol, 2013, 50(6): 1441-1449, DOI
61	Swetnam TW, Lynch AM. A tree-ring reconstruction of western spruce budworm history in the southern rocky mountains. For Sci, 1989, 35(4): 962-986, DOI
62	Tang XZ, Machimura T, Li JF, Liu W, Hong HY. A novel optimized repeatedly random undersampling for selecting negative samples: a case study in an SVM-based forest fire susceptibility assessment. J Environ Manag, 2020, 271, DOI
63	Tanja S, Berninger F, Vesala T, Markkanen T, Hari P, Mäkelä A, Ilvesniemi H, Hänninen H, Nikinmaa E, Huttula T, Laurila T, Aurela M, Grelle A, Lindroth A, Arneth A, Shibistova O, Lloyd J. Air temperature triggers the recovery of evergreen boreal forest photosynthesis in spring. Glob Change Biol, 2003, 9(10): 1410-1426, DOI
64	Terryn L, Calders K, Disney M, Origo N, Malhi Y, Newnham G, Raumonen P, Å kerblom M, Verbeeck H. Tree species classification using structural features derived from terrestrial laser scanning. ISPRS J Photogramm Remote Sens, 2020, 168: 170-181, DOI
65	Trotsiuk V, Pederson N, Druckenbrod DL, Orwig DA, Bishop DA, Barker-Plotkin A, Fraver S, Martin-Benito D. Testing the efficacy of tree-ring methods for detecting past disturbances. For Ecol Manag, 2018, 425: 59-67, DOI
66	Wang HL, Shao XM, Li MQ. A 2917-year tree-ring-based reconstruction of precipitation for the buerhanbuda mts., Southeastern Qaidam Basin, China. Dendrochronologia, 2019, 55: 80-92, DOI
67	Wang J, Feng L, Palmer PI, Liu Y, Fang SX, Bösch H, O’dell CW, TangYang XPDX, Liu LX, Xia CZ. Large Chinese land carbon sink estimated from atmospheric carbon dioxide data. Nature, 2020, 586(7831): 720-723, DOI
68	Wolff F, Kolari THM, Villoslada M, Tahvanainen T, Korpelainen P, Zamboni PAP, Kumpula T. RGB vs. Multispectral imagery: mapping aapa mire plant communities with UAVs. Ecol Indic, 2023, 148: 110140, DOI
69	Zhang LT, Li ZB, Wang H, Xiao JB. Influence of intra-event-based flood regime on sediment flow behavior from a typical agro-catchment of the Chinese Loess Plateau. J Hydrol, 2016, 538: 71-81, DOI
70	Zhu CM, Wang Z. Entropy-based matrix learning machine for imbalanced data sets. Pattern Recognit Lett, 2017, 88: 72-80, DOI

[1]	Hongxing Liu, Mingyong Li, Ruiyun Han, Xiaolin Zhang, Jinnan Ge, Guangyou Hao. Increased temperatures contribute to early aging of plantation-grown Mongolian pine in introduced areas at lower latitudes [J]. JOURNAL OF FORESTRY RESEARCH, 2024, 35(1): 122-.
[2]	Remzi Eker, Kamber Can Alkiş, Abdurrahim Aydın. Assessment of large-scale multiple forest disturbance susceptibilities with AutoML framework: an Izmir Regional Forest Directorate case [J]. JOURNAL OF FORESTRY RESEARCH, 2024, 35(1): 65-.
[3]	Teng Li, Jianfeng Peng, Tsun Fung Au, Jinbao Li. April–September minimum temperature reconstruction based on Sabina tibetica ring-width chronology in the central eastern Tibetan Plateau, China [J]. JOURNAL OF FORESTRY RESEARCH, 2024, 35(1): 37-.
[4]	Teng Li, Jianfeng Peng, Tsun Fung Au, Jingru Li, Jinbao Li, Yue Zhang. Dendroclimatological study of Sabina saltuaria and Abies faxoniana in the mixed forests of the Qionglai Mountains, eastern Tibetan Plateau [J]. JOURNAL OF FORESTRY RESEARCH, 2024, 35(1): 20-.
[5]	Bo Gao, Yanlong Shan, Xiangyu Liu, Sainan Yin, Bo Yu, Chenxi Cui, Lili Cao. Prediction and driving factors of forest fire occurrence in Jilin Province, China [J]. JOURNAL OF FORESTRY RESEARCH, 2024, 35(1): 21-.
[6]	Yang Yang. Vibration properties of Paulownia wood for Ruan sound quality using machine learning methods [J]. JOURNAL OF FORESTRY RESEARCH, 2024, 35(1): 9-.
[7]	Sohee Park, A-Ram Yang, Eun-hee Kim, Joongbin Lim. Model development to estimate site index values for six major tree species in North Korea [J]. JOURNAL OF FORESTRY RESEARCH, 2023, 34(2): 387-400.