Comparing rotation forests and extreme gradient boosting for monitoring drought damage on KwaZulu-Natal commercial forests

References

• Agri SA. 2016. A raindrop in the drought. Report to the multi-stakeholder task team on the drought. Pretoria: Government Printer.
   Google Scholar
• Akar Ö. 2018. The rotation forest algorithm and object-based classification method for land use mapping through UAV images. Geocarto Int. 33(5):538–553.
   Web of Science ®Google Scholar
• Al-Hedny SM, Muhaimeed AS. 2020. Drought monitoring for northern part of Iraq using temporal NDVI and rainfall indices. In: Al-Quraishi A, Negm A, editors. Environmental Remote Sensing and GIS in Iraq. New York: Springer.
   Google Scholar
• Amalo LF, Hidayat R. 2017. Comparison between remote-sensing-based drought indices in east java. IOP Conference Series: Earth and Environmental Science. IOP Publishing.
   Google Scholar
• Bajocco S, Ferrara C, Alivernini A, Bascietto M, Ricotta C. 2019. Remotely-sensed phenology of Italian forests: going beyond the species. Int J Appl Earth Obs Geoinf. 74:314–321.
   Web of Science ®Google Scholar
• Bayissa YA, Tadesse T, Svoboda M, Wardlow B, Poulsen C, Swigart J, Van Andel SJ. 2019. Developing a satellite-based combined drought indicator to monitor agricultural drought: a case study for Ethiopia. GISci Remote Sens. 56(5):718–748.
   Web of Science ®Google Scholar
• Bergstra J, Bardenet R, Bengio Y, Kégl B. 2011. Algorithms for hyper-parameter optimization. 25th Annual Conference on Neural Information Processing Systems (NIPS 2011), Granada, Spain. NeurIPS.
   Google Scholar
• Bhuiyan C, Singh RP, Kogan FN. 2006. Monitoring drought dynamics in the Aravalli region (India) using different indices based on ground and remote sensing data. Int J Appl Earth Obs Geoinf. 8(4):289–302.
   Web of Science ®Google Scholar
• Chen T, Guestrin C. 2016. XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD. International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery. San Francisco, CA, USA. p. 785–794.
   Google Scholar
• Colkesen I, Kavzoglu T. 2017. Ensemble-based canonical correlation forest (CCF) for land use and land cover classification using sentinel-2 and Landsat OLI imagery. Remote Sens Lett. 8(11):1082–1091.
   Web of Science ®Google Scholar
• Du L, Tian Q, Yu T, Meng Q, Jancso T, Udvardy P, Huang Y. 2013. A comprehensive drought monitoring method integrating MODIS and TRMM data. Int J Appl Earth Obs Geoinf. 23:245–253.
   Web of Science ®Google Scholar
• Dutrieux LP, Verbesselt J, Kooistra L, Herold M. 2015. Monitoring forest cover loss using multiple data streams, a case study of a tropical dry forest in Bolivia. ISPRS J Photogramm Remote Sens. 107:112–125.
   Web of Science ®Google Scholar
• Edossa DC, Woyessa YE, Welderufael WA. 2014. 2014. Analysis of droughts in the central region of South Africa and their association with SST anomalies. Int J Atmos Sci. 2014:1–8.
   Google Scholar
• Fan J, Wang X, Wu L, Zhou H, Zhang F, Yu X, Lu X, Xiang Y. 2018. Comparison of support vector machine and extreme gradient boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates. A case study in China. Energy Convers Manage. 164:102–111.
   Web of Science ®Google Scholar
• Fassnacht FE, Neumann C, Förster M, Buddenbaum H, Ghosh A, Clasen A, Joshi PK, Koch B. 2014. Comparison of feature reduction algorithms for classifying tree species with hyperspectral data on three central European test sites. IEEE J Sel Top Appl Earth Obs Remote Sens. 7(6):2547–2561.
   Web of Science ®Google Scholar
• Gao B-C. 1996. NDWI—a normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sens Environ. 58(3):257–266.
   Web of Science ®Google Scholar
• Gao X, Huete AR, Ni W, Miura T. 2000. Optical–biophysical relationships of vegetation spectra without background contamination. Remote Sens Environ. 74(3):609–620.
   Web of Science ®Google Scholar
• Gao Y, Quevedo A, Szantoi Z, Skutsch M. 2019. Monitoring forest disturbance using time-series MODIS NDVI in Michoacán, Mexico. Geocarto Int. 1–17.
   Web of Science ®Google Scholar
• Georganos S, Grippa T, Vanhuysse S, Lennert M, Shimoni M, Wolff E. 2018. Very high resolution object-based land use–land cover urban classification using extreme gradient boosting. IEEE Geosci Remote Sens Lett. 15(4):607–611.
   Web of Science ®Google Scholar
• Gulácsi A, Kovács F. 2018. Drought monitoring of forest vegetation using MODIS-based normalized difference drought index in Hungary. HunGeoBull. 67(1):29–42.
   Google Scholar
• Hao Z, AghaKouchak A. 2013. Multivariate standardized drought index: a parametric multi-index model. Adv Water Resour. 57:12–18.
   Web of Science ®Google Scholar
• Hao Z, Singh VP. 2015. Drought characterization from a multivariate perspective: a review. J Hydrol. 527:668–678.
   Web of Science ®Google Scholar
• Heim RR. 2002. A review of twentieth-century drought indices used in the United States. Bull Amer Meteor Soc. 83(8):1149–1166.
   Web of Science ®Google Scholar
• Hlahla S, Hill TR. 2018. Responses to climate variability in urban poor communities in Pietermaritzburg, KwaZulu-Natal, South Africa. SAGE Open. 8(3):215824401880091. 2158244018800914.
   Web of Science ®Google Scholar
• Hope A, Fouad G, Granovskaya Y. 2014. Evaluating drought response of Southern Cape Indigenous Forests, South Africa, using MODIS data. Int J Remote Sens. 35(13):4852–4864.
   Web of Science ®Google Scholar
• Huete A, Didan K, Miura T, Rodriguez EP, Gao X, Ferreira LG. 2002. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sens Environ. 83(1–2):195–213.
   Web of Science ®Google Scholar
• Jewitt D, Goodman PS, O’Connor TG, Erasmus BFN, Witkowski ETF. 2016. Mapping landscape beta diversity of plants across KwaZulu-Natal, South Africa, for aiding conservation planning. Biodivers Conserv. 25(13):2641–2654.
   Web of Science ®Google Scholar
• Jewitt D, Goodman P, Erasmus B, O’Connor T, Witkowski E. 2015. Systematic land-cover change in KwaZulu-Natal, South Africa: implications for biodiversity. S Afr J Sci. 111(9–10).
   Web of Science ®Google Scholar
• Jiao W, Zhang L, Chang Q, Fu D, Cen Y, Tong Q. 2016. Evaluating an enhanced vegetation condition index (VCI) based on VIUPD for drought monitoring in the continental United States. Remote Sens. 8(3):224.
   Web of Science ®Google Scholar
• Jump AS, Cavin L, Hunter PD. 2010. Monitoring and managing responses to climate change at the retreating range edge of forest trees. J Environ Monit. 12(10):1791–1798.
   PubMedGoogle Scholar
• Jury MR. 1998. Statistical analysis and prediction of KwaZulu-Natal climate. Theor Appl Climatol. 60(1–4):1–10.
   Web of Science ®Google Scholar
• Kazllarof V, Karlos S, Kotsiantis S. 2019. Active learning rotation forest for multiclass classification. Comput Intell. 35(4):891–918.
   Web of Science ®Google Scholar
• Keyantash J, Dracup JA. 2002. The quantification of drought: an evaluation of drought indices. Bull Amer Meteor Soc. 83(8):1167–1180.
   Web of Science ®Google Scholar
• Khan J, Wang P, Xie Y, Wang L, Li L. 2018. Mapping MODIS LST NDVI imagery for drought monitoring in Punjab Pakistan. IEEE Access. 6:19898–19911.
   Web of Science ®Google Scholar
• Kogan F. 1990. Remote sensing of weather impacts on vegetation in non-homogeneous areas. Int J Remote Sens. 11(8):1405–1419.
   Web of Science ®Google Scholar
• Kogan F. 2002. World droughts in the new millennium from AVHRR-based vegetation health indices. Eos Trans AGU. 83(48):557–563.
   Google Scholar
• Kogan FN. 1995a. Application of vegetation index and brightness temperature for drought detection. Adv Space Res. 15(11):91–100.
   PubMed Web of Science ®Google Scholar
• Kogan FN. 1995b. Droughts of the late 1980s in the United States as derived from NOAA polar-orbiting satellite data. Bull Am Meteor Soc. 76(5):655–668.
   Web of Science ®Google Scholar
• Kruger A. 2019. Trends in cloud cover from 1960 to 2005 over South Africa. WSA. 33(5):603–608.
   Google Scholar
• Kuncheva LI, Rodríguez JJ. 2007. An experimental study on rotation forest ensembles. International Workshop on Multiple Classifier Systems. Berlin, Heidelberg: Springer. p. 459–468.
   Google Scholar
• Li F, Li H, Lu W, Zhang G, Kim J-C. 2019. Meteorological drought monitoring in Northeastern China using multiple indices. Water. 11(1):72.
   Web of Science ®Google Scholar
• Lijun Z, Zengxiang Z, Tingting D, Xiao W. 2008. Application of MODIS/NDVI and MODIS EVI to extracting the information of cultivated land and comparison analysis. Trans Chin Soc Agr Eng. 2008(3):167–172.
   Google Scholar
• Liu H, Weng Q. 2018. Scaling effect of fused ASTER-MODIS land surface temperature in an urban environment. Sensors. 18(11):4058.
   PubMed Web of Science ®Google Scholar
• Lottering RT, Govender M, Peerbhay K, Lottering S. 2020. Comparing partial least squares (PLS) discriminant analysis and sparse PLS discriminant analysis in detecting and mapping Solanum mauritianum in commercial forest plantations using image texture. ISPRS J Photogramm Remote Sens. 159:271–280.
   Web of Science ®Google Scholar
• Martínez-Vilalta J, Lloret F, Breshears DD. 2012. Drought-induced forest decline: causes, scope and implications. Biol Lett. 8(5):689–691.
   PubMed Web of Science ®Google Scholar
• Mera GA. 2018. Drought and its impacts in Ethiopia. Weather Clim Extremes. 22:24–35.
   Web of Science ®Google Scholar
• Millar CI, Stephenson NL. 2015. Temperate forest health in an era of emerging mega disturbance. Science. 349(6250):823–826.
   PubMed Web of Science ®Google Scholar
• Mohammad K, Jang M-W, Hwang S, Jang T. 2018. Evaluating the agricultural drought for pre-kharif season in Bangladesh using MODIS vegetation health index. J Korean Soc Agr Eng. 60(6):55–63.
   Google Scholar
• Monyela BM. 2017. A two-year long drought in summer 2014/2015 and 2015/2016 over South Africa. Unpublished thesis. Cape Town: University of Cape Town.
   Google Scholar
• Mutanga O, Skidmore AK. 2004. Hyperspectral band depth analysis for a better estimation of grass biomass (Cenchrus ciliaris) measured under controlled laboratory conditions. Int J Appl Earth Obs Geoinf. 5(2):87–96.
   Google Scholar
• Narkhede S. 2018. Understanding AUC-ROC curve. [Internet]. Towards Data Sci. 26. Available from: https://towardsdatascience.com/understanding-auc-roc-curve-68b2303cc9c5. [Accessed: 15 May 2020].
   Google Scholar
• Peters AJ, Walter-Shea EA, Ji L, Vina A, Hayes M, Svoboda MD. 2002. Drought monitoring with NDVI-based standardized vegetation index. Photogramm Eng Remote Sens. 68(1):71–75.
   Web of Science ®Google Scholar
• Pontius RG, Millones M. 2011. Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment. Int J Remote Sens. 32(15):4407–4429.
   Web of Science ®Google Scholar
• Qiu J, Yang J, Wang Y, Su H. 2018. A comparison of NDVI and EVI in the DisTrad model for thermal sub-pixel mapping in densely vegetated areas: a case study in Southern China. Int J Remote Sens. 39(8):2105–2118.
   Web of Science ®Google Scholar
• Reid P, Vogel C. 2006. Living and responding to multiple stressors in South Africa—Glimpses from KwaZulu-Natal. Global Environ Change. 16(2):195–206.
   Web of Science ®Google Scholar
• Rodriguez JJ, Kuncheva LI, Alonso CJ. 2006. Rotation forest: a new classifier ensemble method. IEEE Trans Pattern Anal Mach Intell. 28(10):1619–1630.
   PubMed Web of Science ®Google Scholar
• Rojas O, Vrieling A, Rembold F. 2011. Assessing drought probability for agricultural areas in Africa with coarse resolution remote sensing imagery. Remote Sens Environ. 115(2):343–352.
   Web of Science ®Google Scholar
• Rouault M, Richard Y. 2005. Intensity and spatial extent of droughts in southern Africa. Geophys Res Lett. 32(15).
   Web of Science ®Google Scholar
• Sahu AS. 2014. Identification and mapping of the water-logged areas in Purba Medinipur part of Keleghai river basin, India: RS and GIS methods. Int J Adv Geosci. 2(2):59–65.
   Google Scholar
• Sandino J, Gonzalez F, Mengersen K, Gaston KJ. 2018. UAVs and machine learning revolutionising invasive grass and vegetation surveys in remote arid lands. Sensors. 18(2):605.
   Web of Science ®Google Scholar
• Singh Rawat K, Sehgal VK, Ray SS. 2019. Downscaling of MODIS thermal imagery. Egyptian J Remote Sens Space Sci. 22(1):49–58.
   Web of Science ®Google Scholar
• Solh M, van Ginkel M. 2014. Drought preparedness and drought mitigation in the developing world’s drylands. Weather Clim Extremes. 3:62–66.
   Google Scholar
• Sun S, Qiu L, He C, Li C, Zhang J, Meng P. 2018. Drought-affected Populus simonii Carr. show lower growth and long-term increases in intrinsic water-use efficiency prior to tree mortality. Forests. 9(9):564.
   Web of Science ®Google Scholar
• Testa S, Soudani K, Boschetti L, Borgogno Mondino E. 2018. MODIS-derived EVI, NDVI and WDRVI time series to estimate phenological metrics in French deciduous forests. Int J Appl Earth Obs Geoinf. 64:132–144.
   Web of Science ®Google Scholar
• Tucker CJ. 1979. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sens Environ. 8(2):127–150.
   Web of Science ®Google Scholar
• Verma P, Raghubanshi A, Srivastava PK, Raghubanshi AS. 2020. Appraisal of kappa-based metrics and disagreement indices of accuracy assessment for parametric and nonparametric techniques used in LULC classification and change detection. Model Earth Syst Environ. 6(2):1045–1059.
   Web of Science ®Google Scholar
• Wainwright HM, Steefel C, Trutner SD, Henderson AN, Nikolopoulos EI, Wilmer CF, Chadwick KD, Falco N, Schaettle KB, Brown JB, et al. 2020. Satellite-derived foresummer drought sensitivity of plant productivity in Rocky Mountain headwater catchments: spatial heterogeneity and geological-geomorphological control. Environ Res Lett. 15(8):084018.
   Web of Science ®Google Scholar
• Wang M, Gu Q, Liu G, Shen J, Tang X. 2019. Hydrological condition constrains vegetation dynamics for wintering waterfowl in China’s East Dongting Lake wetland. Sustainability. 11(18):4936.
   Web of Science ®Google Scholar
• Wardlow BD, Egbert SL. 2010. A comparison of MODIS 250-m EVI and NDVI data for crop mapping: a case study for southwest Kansas. Int J Remote Sens. 31(3):805–830.
   Web of Science ®Google Scholar
• Warrens MJ. 2015. Relative quantity and allocation disagreement measures for category-level accuracy assessment. Int J Remote Sens. 36(23):5959–5969.
   Web of Science ®Google Scholar
• Wilhite D. 2005. Drought and water crisis: science, technology, and management issues; p. 406.
   Google Scholar
• Wilhite DA, Glantz MH. 1985. Understanding: the drought phenomenon: the role of definitions. Water Int. 10(3):111–120.
   Google Scholar
• Wu D, Qu JJ, Hao X. 2015. Agricultural drought monitoring using MODIS-based drought indices over the USA Corn Belt. Int J Remote Sens. 36(21):5403–5425.
   Web of Science ®Google Scholar
• Xia J, Du P, He X, Chanussot J. 2014. Hyperspectral remote sensing image classification based on rotation forest. IEEE Geosci Remote Sensing Lett. 11(1):239–243.
   Web of Science ®Google Scholar
• Xia Y, Liu C, Li Y, Liu N. 2017. A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring. Expert Syst Appl. 78:225–241.
   Web of Science ®Google Scholar
• Xulu S, Peerbhay K, Gebreslasie M, Ismail R. 2018. Drought influence on forest plantations in Zululand, South Africa, using MODIS time series and climate data. Forests. 9(9):528.
   Web of Science ®Google Scholar
• Zambrano F, Lillo-Saavedra M, Verbist K, Lagos O. 2016. Sixteen years of agricultural drought assessment of the BioBío region in Chile using a 250 m resolution Vegetation Condition Index (VCI). Remote Sens. 8(6):530.
   Web of Science ®Google Scholar
• Zengir VS, Sobhani B, Asghari S. 2020. Monitoring and investigating the possibility of forecasting drought in the western part of Iran. Arabian J Geosci. 13(12):1–12.
   Web of Science ®Google Scholar
• Zhang F, Du B, Zhang L. 2016. Scene classification via a gradient boosting random convolutional network framework. IEEE Trans Geosci Remote Sens. 54(3):1793–1802.
   Web of Science ®Google Scholar
• Zhang L, Jiao W, Zhang H, Huang C, Tong Q. 2017. Studying drought phenomena in the Continental United States in 2011 and 2012 using various drought indices. Remote Sens Environ. 190:96–106.
   Web of Science ®Google Scholar
• Zhang M, Yuan X, Otkin JA. 2020. Remote sensing of the impact of flash drought events on terrestrial carbon dynamics over China. Carbon Balance Manag. 15(1):20.
   PubMed Web of Science ®Google Scholar
• Zhang Y, Peng C, Li W, Fang X, Zhang T, Zhu Q, Chen H, Zhao P. 2013. Monitoring and estimating drought-induced impacts on forest structure, growth, function, and ecosystem services using remote-sensing data: recent progress and future challenges. Environ Rev. 21(2):103–115.
   Google Scholar
• Zhuo W, Huang J, Zhang X, Sun H, Zhu D, Su W, Zhang C, Liu Z. 2016. Comparison of five drought indices for agricultural drought monitoring and impacts on winter wheat yields analysis. In: 2016 Fifth International Conference on Agro-Geoinformatics (Agro-Geoinformatics). IEEE. p. 1–6.
   Google Scholar
• Zou L, Cao S, Sanchez-Azofeifa A. 2020. Evaluating the utility of various drought indices to monitor meteorological drought in Tropical Dry Forests. Int J Biometeorol. 64(4):701–711.
   PubMed Web of Science ®Google Scholar
• Zucchini W, Adamson PT. 1984. The occurrence and severity of droughts in South Africa. South African Water Research Commission Report 91/1/84.
   Google Scholar