Modeling of spectral monitoring of cotton aphid population based on feature bands

Authors

  • Jiao LIN Tarim University, College of Agronomy, Alar 843300, Xinjiang; Key Laboratory of Genetic Improvement and Efficient Production for Specialty Crops in Arid Southern Xinjiang of Xinjiang Corps, Alar 843300, Xinjiang (CN)
  • Zi-Wei BAI Tarim University, College of Agronomy, Alar 843300, Xinjiang; Key Laboratory of Genetic Improvement and Efficient Production for Specialty Crops in Arid Southern Xinjiang of Xinjiang Corps, Alar 843300, Xinjiang (CN)
  • Jia-Qi ZHANG Tarim University, College of Agronomy, Alar 843300, Xinjiang; Key Laboratory of Genetic Improvement and Efficient Production for Specialty Crops in Arid Southern Xinjiang of Xinjiang Corps, Alar 843300, Xinjiang (CN)
  • Qiang HU Tarim University, College of Agronomy, Alar 843300, Xinjiang; Key Laboratory of Genetic Improvement and Efficient Production for Specialty Crops in Arid Southern Xinjiang of Xinjiang Corps, Alar 843300, Xinjiang (CN)
  • Nan CAO Tarim University, College of Agronomy, Alar 843300, Xinjiang; Key Laboratory of Genetic Improvement and Efficient Production for Specialty Crops in Arid Southern Xinjiang of Xinjiang Corps, Alar 843300, Xinjiang (CN)
  • Su-Mei WAN Tarim University, College of Agronomy, Alar 843300, Xinjiang; Key Laboratory of Genetic Improvement and Efficient Production for Specialty Crops in Arid Southern Xinjiang of Xinjiang Corps, Alar 843300, Xinjiang (CN)

DOI:

https://doi.org/10.15835/nbha52414099

Keywords:

cotton aphid, feature band, machine learning, modelling, population

Abstract

Cotton aphid is the most common and harmful insect in the process of cotton growth and development, and it is the most serious pest that restricts the high yield and high quality of cotton in China and even in the world. The field-scale experiments were conducted for two years to estimate the population of cotton aphids model on cotton leaves using remote sensing. Hyperspectral data from single leaves and aphid populations were obtained at different growth stages of various cotton varieties. Preprocessing techniques including savitzky-golay (SG), first derivative (FD), second derivative (SD), logarithm transformation (LG), and reciprocal transformation (RG) were applied to the original spectral data. The successive projections algorithm (SPA) combined with the Pearson correlation coefficient (Pearson) method were used to construct three types of hyperspectral monitoring models: linear regression (LR), Extreme gradient boosting (XGBoost), and partial least squares regression (PLSR). Results indicated that LG significantly improved model accuracy, while SPA effectively reduced the number of bands required for analysis. Among the three models constructed using selected feature bands, the XGBoost model outperforms LR and PLSR models in terms of prediction accuracy. LG-Person-XGBoost identified ten feature bands with a coefficient of determination (R2), root mean square error (RMSE), and relative percent deviation (RPD) values reaching 0.76, 65.74 heads/leaf, and 0.91 respectively for the modeling set; whereas predicted R2, RMSE, and RPD values were found to be 0.36, 57.62 heads/leaf, and 0.99 respectively. LG-SPA-XGBoost achieved superior prediction accuracy by selecting eight feature bands with R2, RMSE, and RPD values reaching 0.87, 46.7 heads/leaf, and 1.43 respectively for the modeling set; whereas predicted R2, RMSE, and RPD values were found to be 0.77, 42.66 heads/leaf, and 1.27 respectively. This indicates that the hyperspectral remote sensing model can be used to estimate the population of cotton aphids on cotton leaves based on the selection of feature bands providing are reference for the nondestructive monitoring of cotton aphids in cotton fields and offering a significant supplement to the traditional methods of crop pest quantity monitoring.

References

Cai HH (2022). Research on soil nutrient detection and fertilizer formulation in jujube orchards based on hyperspectral technology. MSc Dissertation, Tarim University. https://doi.org/10.27708/d.cnki.gtlmd.2022.000435

Chen PC (2006). Application of Groung-based Hyperspectral Remote Sensing to Detect Spider Mite. MSc Dissertation, Shihezi University. https://doi.org/10.7666/d.y941979

Dilixiati YMM, Zhou JP, Xu Y, Fan XP, Yalikun SWT (2022). Cotton pest monitoring based on logistic algorithm and remote sensing image. Journal of South China Agricultural University 43(02):87-95. https://doi.org/10.7671/j.issn.1001-411X.202106004

Döring TF, Kirchner SM (2022). A model for colour preference behaviour of spring migrant aphids[J]. Philosophical Transactions of the Royal Society B 377(1862):20210283. https://doi.org/10.1098/rstb.2021.0283

Felipe DOD, Sarvio DVM, Tavares CO, Franoise DD, Mariane GFC, Carlos N (2023). Remote sensing and machine learning techniques for high throughput phenotyping of late blight-resistant tomato plants in open field trials. International Journal of Remote Sensing 44(6):1900-1921. https://doi.org/10.1080/01431161.2023.2192878

Feng LK, Gao GZ, Lv ZZ, Jia HM, Wang PL (2015). Interspecific competition between Aphis gossypii glover and Acyrthosiphon gossypii Mordviiko at different temperatures. Journal of Applied Insects 52(03):557-565. https://doi.org/CNKI:SUN:KCZS.0.2015-03-004

Gao ZH, Bai LN, Wang BY, Li ZY, Li XS, Wang YK (2011). Estimation of soil organic matter content in desertified landsusing measured soil spectral data. Forestry Science 47(06):9-16. https://doi.org/10.11707/j.1001-7488.20110602

Gomez SK, Oosterhuis DM, Hendrix DL, Johnson DJ Steinkraus DC (2006). Diurnal pattern of aphid feeding and its effect on cotton leaf physiology. Environmental and Experimental Botany 55(1-2):77-86. https://doi.org/10.1016/j.envexpbot.2004.10.001

Guo P, Wu FD, Dai JG, Wang HJ, Xu LP, Zhang GS (2017). Comparison of farmland crop classification methods based on visible light images of unmanned aerial vehicles. Journal of Agricultural Engineering 33(13):112-119. https://doi.org/10.11975/j.issn.1002-6819.2017.13.015

Guo YS, Liu QS, Liu GH, Huang C (2017). Extraction of main crops in yellow river delta based on MODIS NDVI time series. Journal of Natural Resources 32(10):1808-1818. https://doi.org/10.11849/zrzyxb.20160943

Hu HY, Ren XL, Jiang WL, Ma XY, Ma YJ, Wang D,Ma T (2018). Pesticide spray distribution of plant protection UVA in cotton field. Journal of Huazhong Agricultural University 2018,37(05):59-64. https://doi.org/10.13300/j.cnki.hnlkxb.20180622.007

Kong YR, Wang LJ, Feng HK, Xu Y, Liang L, Xu L, Yang XD, Zhang QQ (2022). Leaf area index estimation based on UAV hyperspectral band selection. Spectroscopy and Spectral Analysis 42(03):933-939. https://doi.org/10.3964/j.issn.1000-0593(2022)03-0933-07

LACITIGNOL D, TEBALDI C (2005). Effects of ecological differentiation on Lotka–Volterra systems for species with behavioral adaptation and variable growth rates. Mathematical Biosciences 194(1):95-123. https://doi.org/10.1016/j.mbs.2004.10.012

Liao J, Tao WY, Zang Y, Zeng HY, Wang P, Luo XW (2023). Research progress and prospect of key technologies in crop disease and insect pest monitoring. Transactions of the Chinese Society for Agricultural Machinery 54 (11):1-19. https://doi.org/10.6041/j.issn.1000-1298.2023.11.001

Liu J, Wang LM, Yang FG, Yang LB, Wang XL (2015). Remote sensing estimation of crop planting area based on HJ time-series images. Journal of Agricultural Engineering 31(3):199-206. https://doi.org/10.3969/j.issn.1002-6819.2015.03.026

Lu LM (2019). Prediction of Soil Properties Based on Hyperspectral Characteristic. MSc Dissertation, Anhui University of Science and Technology.

Luo JY, Cui JJ, Huang Q (2011). The relationship between the content of cotton leaf chlorophyll and waxiness and leaf thickness and the cotton resistance to Apolygus lucorum. Journal of Plant Protection 38(04):320-326. https://doi.org/10.13802/j.cnki.zwbhxb.2011.04.016

National Bureau of Statistics. https://www.stats.gov.cn/sj/zxfb/202312/t20231225_1945745.html

Niu FP, Li XG, Maimaitituerxun AZT, Zhao H (2021). Hyperspectral estimation of soil organic carbon content in the West Lakeside Oasis of Bosten Lakebased on successive projection algorithm. Journal of Zhejiang University (Agriculture and Life Sciences) 47(05):673-682. https://doi.org/10.3785/j.issn.1008-9209.2021.01.181

Pei PC (2019). Study on monitoring of cotton aphids damage level based on UVA hyperspectral images. MSc Dissertation, Henan Agricultural University. https://doi.org/10.27117/d.cnki.ghenu.2019.000186

Shukla KK, Nigam R, Birah A, Kanojia AK, Kumar A, Bhattacharya BK, Chander S (2023). Detection of aphid-infested mustard crop using ground spectroscopy. Remote Sensing 16(1):47. https://doi.org/10.3390/rs16010047

Wan Y (2023). Research and application of correlation analysis in wavelength selection in near-infrared spectroscopy. MSc Dissertation, Heilongjiang Bayi Agricultural University.

Wang CH (2020). Exploration of comprehensive prevention and control technology for cotton diseases and pests. China Cotton Processing (06):28-30. https://doi.org/10.3969/j.issn.1003-0662.2020.06.011

Wang PX, Xun L, Li L, Xie Y, Wang L (2017). Extraction of planting areas of main crops based on fourier transformed characteristics of time series leaf area index products. Journal of Agricultural Engineering 33(21):207-215. https://doi.org/CNKI:SUN:NYGU.0.2017-21-025

Wang QL (2015). Prediction Soil Total Nitrogen Based on the Soil Visible Near Infrared Spectral Library. MSc Dissertation, Zhejiang University.

Wang SD, Shi PJ, Zhang HB, Wang XC (2019). Retrieval of soil total nitrogen content in reclaimed farmland of mining area based on hyperspectral imaging. Chinese Journal of Ecology 38(01):294-301. https://doi.org/10.13292/j.1000-4890.201901.034

Wang SQ (2021). Study on Variation Characteristics and Estimation Modeling of Cotton Leaf Nitrogen Based on Hyperspectral. MSc Dissertation, Tarim University.

Xie YT, Plett D, Evans M, Garrard T, Butt M, Clarke K, Liu HJ (2024). Hyperspectral imaging detects biological stress of wheat for early diagnosis of crown rot disease. Computers and Electronics in Agriculture 217108571-.https://doi.org/10.1016/J.COMPAG.2023.108571

Xu JC (2020). The Research and Application of Monitoring Method of Cotton Aphid Hazard Based on Hyperspectral Imaging. MSc Dissertation, Shihezi University. https://doi.org/10.27332/d.cnki.gshzu.2020.000679

Yuan L (2015). Identification and Differentiation of Wheat Diseases and Insects with Multi-source and Multi-scale Remote Sensing Data[D]. PhD Thesis, Zhejiang University.

Zeng HL, Ye PS, He L, Jiang QP, Liu CH, Wei SG, Zhang QF, Dai SD, Li QY (2015). Occurrence and control strategies of seedling insect pests for transgenic insect-resistant cotton. Chinese Cotton Society. Compilation of Papers from the 2015 Annual Conference of the Chinese Cotton Society. Sichuan Academy of Agricultural Sciences Economic Crop Breeding and Cultivation Research Institute, 2015:218-219.

https://navi.cnki.net/knavi/conferences/proceedings/MHXB201508002/detail?uniplatform=NZKPT

Zhang Q, Li XC, Yu L, Zhao BM, L H (2020). Analysis on the Occurrence and cause of main cotton diseases and insect pests in Xinjiang Production and construction corps in 2020. China Cotton 47(12):38-40. https://doi.org/10.11963/1000-632X.zqlh.20201207

Zhang ZG (2011). The Early Identification of Remote Sensing about Bursaphelenchus Xylophilus Based on Process Model. MSc Dissertation, Beijing Forestry University.

Zhao Q, Zhang GL, Chen XD (2005). Effects of multiplicative scatter correction on a calibration model of near infrared spectral analysis. Optics and Precision Engineering (01):53-58. https://doi.org/10.3321/j.issn:1004-924X.2005.01.010

Zhou YG, Wang JG, Ma TW, He ZM (2011). Effects of Mepiquat Chloride (DPC) on species reproduction of aphis gossypii glover. Acta Agriculturae Boreali-Occidentalis Sinica 20(05):199-202. https://doi.org/10.3969/j.issn.1004-1389.2011.05.039

Downloads

Published

2024-12-18

How to Cite

LIN, J., BAI, Z.-W., ZHANG, J.-Q., HU, Q., CAO, N., & WAN, S.-M. (2024). Modeling of spectral monitoring of cotton aphid population based on feature bands. Notulae Botanicae Horti Agrobotanici Cluj-Napoca, 52(4), 14099. https://doi.org/10.15835/nbha52414099

Issue

Section

Research Articles
CITATION
DOI: 10.15835/nbha52414099