Using satellite-measured relative humidity for prediction of Metisa plana’s population in oil palm plantations: A comparative assessment of regression and artificial neural network models


Autoři: Siti Aisyah Ruslan aff001;  Farrah Melissa Muharam aff001;  Zed Zulkafli aff003;  Dzolkhifli Omar aff004;  Muhammad Pilus Zambri aff005
Působiště autorů: Department of Agriculture Technology, Faculty of Agriculture, Universiti Putra Malaysia, Serdang, Selangor, Malaysia aff001;  Institute of Plantation Studies, Universiti Putra Malaysia, Serdang, Selangor, Malaysia aff002;  Department of Civil Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang, Selangor, Malaysia aff003;  Department of Plant Protection, Faculty of Agriculture, Universiti Putra Malaysia, Serdang, Selangor, Malaysia aff004;  Department of Agronomy and Innovation, TH Plantations Berhad, Kuala Lumpur, Wilayah Persekutuan, Malaysia aff005
Vyšlo v časopise: PLoS ONE 14(10)
Kategorie: Research Article
doi: 10.1371/journal.pone.0223968

Souhrn

Metisa plana (Walker) is a leaf defoliating pest that is able to cause staggering economical losses to oil palm cultivation. Considering the economic devastation that the pest could bring, an early warning system to predict its outbreak is crucial. The state of art of satellite technologies are now able to derive environmental factors such as relative humidity (RH) that may influence pest population’s fluctuations in rapid, harmless, and cost-effective manners. This study examined the relationship between the presence of Metisa plana at different time lags and remote sensing (RS) derived RH by using statistical and machine learning approaches. Metisa plana census data of cumulated larvae instar 1, 2, 3, and 4 were collected biweekly in 2014 and 2015 in an oil palm plantation in Muadzam Shah, Pahang, Malaysia. Relative humidity values derived from Moderate Resolution Imaging Spectroradiometer (MODIS) satellite images were apportioned to 6 time lags; 1 week (T1), 2 weeks (T2), 3 week (T3), 4 weeks (T4), 5 week (T5) and 6 weeks (T6) and paired with the respective census data. Pearson’s correlation was carried out to analyse the relationship between Metisa plana and RH at different time lags. Regression analyses and artificial neural network (ANN) were also conducted to develop the best prediction model of Metisa plana’s outbreak. The results showed relatively high correlations, positively or negatively, between the presences of Metisa plana with RH ranging from 0.46 to 0.99. ANN was found to be superior to regression models with the adjusted coefficient of determination (R2) between the actual and predicted Metisa plana values ranging from 0.06 to 0.57 versus 0.00 to 0.05. The analysis on the best time lags illustrated that the multiple time lags were more influential on the Metisa plana population than the individual time lags. The best Metisa plana prediction model was derived from T1, T2 and T3 multiple time lags modelled using the ANN algorithm with R2 value of 0.57, errors below 1.14 and accuracies above 93%. Based on the result of this study, the elucidation of Metisa plana’s landscape ecology was possible with the utilization of RH as the predictor variable in consideration of the time lag effects of RH on the pest’s population.

Klíčová slova:

Artificial neural networks – Census – Forecasting – Humidity – Oil palm – Polynomials – Regression analysis – Vapors


Zdroje

1. Basri MW, Abdul Halim H, Masijan Z. Bagworms (Lepidoptera: Psychidae) of oil palms in Malaysia. PORIM Occasional Paper (Vol. 23). 1988.

2. Tuck HC, Ibrahim Y, Chong KK. Infestations by the bagworms Metisa plana and Pteroma pendula for the period 1986–2000 in major oil palm estates managed by Golden Hope Plantation Berhad in Peninsular Malaysia. J Oil Palm Res. 2011;23: 1040–1050.

3. Basri MW. Life history, ecology, and economic impact of the bagworm, Metisa plana Walker (Lepidoptera; Psychidae) on the oil palm. Ph.D. Thesis, The University of Guelph. 1993. Available from: http://malcat.uum.edu.my/kip/Record/ukm.vtls000136026

4. Wood BJ, Corley RHV, Goh KH. Studies on the effect of pest damage on oil palm yield. In: Kuala Lumpur, Malaysia. The Incorporated Society of Planters; 1973. pp. 360–379.

5. Godfrey LD, Holtzer TO, Norman JM. Effects of European corn borer (Lepidoptera: Pyralidae) tunneling and drought stress on field corn gas exchange parameters. J Econ Entomol. 1991;84: 1370–1380. doi: 10.1093/jee/84.4.1370

6. Ofomata VC, Overholt WA, Lux SA, Huis AV, Egwuatu RI. Comparative studies on the fecundity, egg survival, larval feeding, and development of Chilo partellus and Chilo orichalcociliellus (Lepidoptera: Crambidae) on five grasses. Ecol Popul Biol. 2000;93: 492–499.

7. Tamiru A, Getu E, Jembere B, Bruce T. Effect of temperature and relative humidity on the development and fecundity of Chilo partellus (Swinhoe) (Lepidoptera: Crambidae). Bull Entomol Res. 2012;102: 9–15. doi: 10.1017/S0007485311000307 21672294

8. Guarneri AA, Lazzari C, Diotaiuti L, Lorenzo MG. The effect of relative humidity on the behaviour and development of Triatoma brasiliensis. Physiol Entomol. 2002;27: 142–147. doi: 10.1046/j.1365-3032.2002.00279

9. Gullan P.J, Cranston P. The Insects: An Outline of Entomology. Blackwell Publishing Ltd; 2004.

10. Hirose E, Panizzi AR, Cattelan AJ. Effect of relative humidity on emergence and on dispersal and regrouping of first instar Nezara viridula (L.) (Hemiptera: Pentatomidae). Neutrop. Entomol. 2006: 35: 757–761. doi: 10.1590/S1519-566X2006000600006

11. Norhisham AR, Abood F, Rita M, Hakeem KR. Effect of humidity on egg hatchability and reproductive biology of the bamboo borer (Dinoderus minutus fabricius). Springerplus.2013;2: 2–6. doi: 10.1186/2193-1801-2-2 23459680

12. Luz C, Fargues J. Temperature and moisture requirements for conidial germination of an isolate of Beauveria bassiana, pathogenic to Rhodnius prolixus. Mycopathologia. 1997;138: 117–125. doi: 10.1023/A:1006803812504 16283112

13. Shipp JL, Zhang Y, Hunt DWA, Ferguson G. Influence of humidity and greenhouse microclimate on the efficacy of Beauveria bassiana (Balsamo) for control of greenhouse arthropod pests. Environ Entomol. 2003;32: 1154–1163. doi: 10.1603/0046-225X-32.5.1154

14. Mishra S, Kumar P, Malik A. Effect of temperature and humidity on pathogenicity of native Beauveria bassiana isolate against Musca domestica L. J Parasitic Dis. 201;39: 697–704. doi: 10.1007/s12639-013-0408-0 26688637

15. Sajap AS, Siburat S. Incidence of entomogenous fungi in the bagworm, Pteroma pendula (Lepidoptera: Psychidae), a pest of Acacia mangium. J Plant Proc in the Tropics. 1992; 9: 105–110.

16. Fargues J, Luz C. Effects of fluctuating moisture and temperature regimes on the infection potential of Beauveria bassiana for Rhodnius prolixus. J Invertebr Pathol 2000;75: 202–211. doi: 10.1006/jipa.1999.4923 10753596

17. Wood FH, Foot MA. Graphical analysis of lag in population reaction to environmental change. New Zeal J Ecol. 1981; 4: 45–51.

18. Karpakakunjaram V, Kolathar DM, Muralirangan MC. Effects of abiotic factors on the population of an aciridid grasshopper, Diabolocotantops pingus (Orthoptera: Acrididae) at two sites in southern India: a three year study. J Orthoptera Res. 2002;11: 55–62.

19. Intachat J, Holloway JD, Staines H. Effects of weather and phenology on the abundance and diversity of geometroid moths in a natural Malaysian tropical rain forest. J Trop Ecol. 2001;17: 411–429.

20. Sprintsin M, Chen JM, Czurylowicz P. Combining land surface temperature and shortwave infrared reflectance for early detection of mountain pine beetle infestations in western Canada. J Appl Remote Sens. 2011;5: 1–13.

21. Blum M, Lensky IM, Rempoulakis P, Nestel D. Modeling insect population fluctuations with satellite land surface temperature. Ecol Model. 2015;311: 39–47.

22. Blum M, Nestel D, Cohen Y, Goldshtein E, Helman D, Lensky IM. Predicting Heliothis (Helicoverpa armigera) pest population dynamics with an age-structured insect population model driven by satellite data. Ecol Model. 2018;369: 1–12.

23. Yones MS, Arafat S, Hadid AFA, Elrahman HAA, Dahi H F. Determination of the best timing for control application against cotton leaf worm using remote sensing and geographical information techniques. Egypt J Remote Sens Sp Sci. 2012;15: 151–160.

24. Marques da Silva JR, Damásioe CV, Sousaa AMO, Bugalhof L, Pessanhaf L, Quaresmaa P. Agriculture pest and disease risk maps considering MSG satellite data and land surface temperature. Int J Appl Earth Obs. 2015;38: 40–50.

25. Paruelo JM, Tomasel F. Prediction of functional characteristics of ecosystems: a comparison of artificial neural networks and regression models. Ecol Modell. 1997;97: 173–186. doi: 10.1016/S0304-3800(96)01913-8

26. Sahin M, Kaya Y, Uyar M. Comparison of ANN and MLR models for estimating solar radiation in Turkey using NOAA/AVHRR data. Adv Space Res. 2013;51: 891–904. doi: 10.1016/j.asr.2012.10.010

27. Lee KY, Chung N, Hwang S. Application of an artificial neural network (ANN) model for predicting mosquito abundances in urban areas. Ecol Inform. 2016;36: 172–180. doi: 10.1016/j.ecoinf.2015.08.011

28. Mishra M, Bhavyashree S, Sharma HL. Comparative study of the performance of artificial neural network and multiple linear regression techniques for predicting the soybean yield using its attributing characters. Int Q J of Life Sci. 2017;12: 177–181.

29. Patil J, Mytri VD. A prediction model for population dynamics of cotton pest (Thrips tabaci Linde) using multilayer-perceptron neural network. Int J Comput Appl. 2013;67: 19–26. doi: 10.5120/11384-6663

30. Watts MJ, Worner SP. Using artificial neural networks to determine the relative contribution of abiotic factors influencing the establishment of insect pest species. Ecol Inform. 2007;3: 64–74. doi: 10.1016/j.ecoinf.2007.06.004

31. Yang L, Peng L, Zhang L, Zhang L, Yang S. A prediction model for population occurrence of paddy stem borer (Scirpophaga incertulas), based on back propogation artificial neural network and principal components analysis. Comp Electron Agri. 2009;68: 200–206. doi: 10.1016/j.compag.2009.06.003

32. Tonnang HEZ, Nedorezov LV, Owino JO, Ochanda H, and Löhr B. Host-parasitoid population density prediction using artificial neural networks: diamondback moth and its natural enemies. Agri For Entomol. 2010;12: 233–242. doi: 10.1111/j.1461-9563.2009.00466

33. Tailliez B, Koffi CB. A method for measuring oil palm leaf area. Oleagineux. 1992;47: 537–545.

34. Kok CC, Eng OK, Razak AR, Arshad AM. Microstructure and life cycle of Metisa plana Walker (Lepidoptera: Psychidae). J Sustain Sci Manag. 2011;6: 51–59.

35. Peng G, Li J, Chen Y, Norizan AP, Tay L. High-resolution surface relative humidity computation using MODIS image in Peninsular Malaysia. Chinese Geogr Sci. 2006;16: 260–264. doi: 10.1007/s11769-006-0260-6

36. Kaufman YJ, Gao BC. Remote sensing of water vapor in the near IR from EOS/MODIS. IEEE Trans Geosci Remote Sens. 1992;30: 871–884. doi: 10.1109/36.175321

37. Ahmadi P, Muharam FM, Ahmad K, Mansor S, Seman IA. Early detection of ganoderma basal stem rot of oil palms using artificial neural network spectral analysis. Pl Dis. 2017;101: 1009–1016. doi: 10.1094/PDIS-12-16-1699-RE 30682927

38. Ghaffari A, Abdollahi H, Khoshayand MR, Soltani BI, Dadgar A, Raffiee TM. Performance comparison of neural network training algorithms in modeling of bimodal drug delivery. Int J Pharm. 2006;327: 1–2. doi: 10.1016/j.ijpharm.2006.07.033

39. Abramowitz M, Stegun IA. Handbook of mathematical functions with formulas, graphs, and mathematical tables. United States of America, Washington D.C.; 1972.

40. Bitetti R. Simple linear regression: a case study in R. 2018 Jan [cited 2018 July 17]. Available from: https://rpubs.com/bitettir/simpleregression

41. Abyaneh HZ. Evaluation of multivariate linear regression and artificial neural networks in prediction of water quality parameters. J Environ Health Sci Engin. 2014;12: 1–8. doi: 10.1186/2052-336X-12-40 24456676

42. Anwar A, Mikami Y. Comparing accuracy performance of ANN, MLR, and GARCH model in predicting time deposit return of Islamic Bank. Int J Tra Econ Fin. 2011;2: 44–51. doi: 10.7763/IJTEF.2011.V2.77

43. Tuite C, Agapitos A, O’Neill M, Brabazon A. A preliminary investigation of overfitting in evolutionary driven model induction: implications for financial modelling. In: Di Chio C. et al., editors. Applications of evolutionary computation. Torino: EvoApplications; 2011. pp. 120–130.

44. Wylie FR, Speight MR. Insects pests in tropical forestry. CAB International: Wallingford; 2012.


Článek vyšel v časopise

PLOS One


2019 Číslo 10