Predicting F v /F m and evaluating cotton drought tolerance using hyperspectral and 1D-CNN

Congcong Guo; Liantao Liu; Hongchun Sun; Nan Wang; Ke Zhang; Yongjiang Zhang; Jijie Zhu; Anchang Li; Zhiying Bai; Xiaoqing Liu; Hezhong Dong; Cundong Li

doi:10.3389/fpls.2022.1007150

Predicting F _v /F _m and evaluating cotton drought tolerance using hyperspectral and 1D-CNN

Front Plant Sci. 2022 Oct 18:13:1007150. doi: 10.3389/fpls.2022.1007150. eCollection 2022.

Authors

Congcong Guo¹, Liantao Liu¹, Hongchun Sun¹, Nan Wang^{1

2}, Ke Zhang¹, Yongjiang Zhang¹, Jijie Zhu³, Anchang Li¹, Zhiying Bai¹, Xiaoqing Liu¹, Hezhong Dong⁴, Cundong Li¹

Affiliations

¹ State Key Laboratory of North China Crop Improvement and Regulation/Key Laboratory of Crop Growth Regulation of Hebei Province/College of Agronomy, Hebei Agricultural University, Baoding, China.
² Institute of Cereal and Oil Crops, Hebei Academy of Agriculture and Forestry Sciences, Shijiazhuang, China.
³ Cotton Research Center, Shandong Key Lab for Cotton Culture and Physiology, Shandong Academy of Agricultural Sciences, Jinan, China.
⁴ College of Mechanical and Electrical Engineering, Hebei Agricultural University, Baoding, Hebei, China.

Abstract

The chlorophyll fluorescence parameter F_v/F_m is significant in abiotic plant stress. Current acquisition methods must deal with the dark adaptation of plants, which cannot achieve rapid, real-time, and high-throughput measurements. However, increased inputs on different genotypes based on hyperspectral model recognition verified its capabilities of handling large and variable samples. F_v/F_m is a drought tolerance index reflecting the best drought tolerant cotton genotype. Therefore, F_v/F_m hyperspectral prediction of different cotton varieties, and drought tolerance evaluation, are worth exploring. In this study, 80 cotton varieties were studied. The hyperspectral cotton data were obtained during the flowering, boll setting, and boll opening stages under normal and drought stress conditions. Next, One-dimensional convolutional neural networks (1D-CNN), Categorical Boosting (CatBoost), Light Gradient Boosting Machines (LightBGM), eXtreme Gradient Boosting (XGBoost), Decision Trees (DT), Random Forests (RF), Gradient elevation decision trees (GBDT), Adaptive Boosting (AdaBoost), Extra Trees (ET), and K-Nearest Neighbors (KNN) were modeled with F _v /F _m. The Savitzky-Golay + 1D-CNN model had the best robustness and accuracy (RMSE = 0.016, MAE = 0.009, MAPE = 0.011). In addition, the F _v /F _m prediction drought tolerance coefficient and the manually measured drought tolerance coefficient were similar. Therefore, cotton varieties with different drought tolerance degrees can be monitored using hyperspectral full band technology to establish a 1D-CNN model. This technique is non-destructive, fast and accurate in assessing the drought status of cotton, which promotes smart-scale agriculture.

Keywords: chlorophyll fluorescence parameter Fv/Fm; cotton; drought tolerance; high-throughput measurement; hyperspectral; one-dimensional convolutional neural network.