Continuous Monitoring of Cotton Stem Water Potential using Sentinel-2 Imagery

Abstract

Monitoring cotton status during the growing season is critical in increasing production efficiency. The water status in cotton is a key factor for yield and cotton quality. Stem water potential (SWP) is a precise indicator for assessing cotton water status. Satellite remote sensing is an effective approach for monitoring cotton growth at a large scale. The aim of this study is to estimate cotton water stress at a high temporal frequency and at a large scale. In this study, we measured midday SWP samples according to the acquisition dates of Sentinel-2 images and used them to build linear-regression-based and machine-learning-based models to estimate cotton water stress during the growing season (June to August, 2018). For the linear-regression-based method, we estimated SWP based on different Sentinel-2 spectral bands and vegetation indices, where the normalized difference index 45 (NDI45) achieved the best performance (R 2 = 0.6269; RMSE = 3.6802 (-1*swp (bars))). For the machine-learning-based method, we used random forest regression to estimate SWP and received even better results (R 2 = 0.6709; RMSE = 3.3742 (-1*swp (bars))). To find the best selection of input variables for the machine-learning-based approach, we tried three different data input datasets, including (1) 9 original spectral bands (e.g., blue, green, red, red edge, near infrared (NIR), and shortwave infrared (SWIR)), (2) 21 vegetation indices, and (3) a combination of original Sentinel-2 spectral bands and vegetation indices. The highest accuracy was achieved when only the original spectral bands were used. We also found the SWIR and red edge band were the most important spectral bands, and the vegetation indices based on red edge and NIR bands were particularly helpful. Finally, we applied the best approach for the linear-regression-based and the machine-learning-based methods to generate cotton water potential maps at a large scale and high temporal frequency. Results suggests that the methods developed here has the potential for continuous monitoring of SWP at large scales and the machine-learning-based method is preferred.have devastating impacts on the environment [3]. For agriculture, drought can endanger food security which can have critical effects on the economy, geopolitics, and society [5]. Drought can also negatively affect agriculture production especially in arid and semiarid regions [6]. Therefore, detecting crop water stress is of vital importance to improve agricultural quality and productivity.Cotton is cultivated in arid and semiarid regions and is the most important fiber crop in the world [7]. Cotton is susceptible to water stress in all growth stages, particularly during the flowering and boll development stages [8]. Moreover, water deficit is an important factor limiting growth and development in cotton, including plant height, leaf and root size, as well as economic yield and fiber quality [8]. To better understand the cotton's response and adaption to water stress, continuous monitoring of cotton water status in large a...

Cotton Classification Method at the County Scale Based on Multi-Features and Random Forest Feature Selection Algorithm and Classifier

“…This is because green plants have strong absorption in the red (R) band and strong reflection in the NIR band. Some studies suggest that red edge and NIR bands are important in crop research [51,52]. However, it is worth mentioning that the value of the spectral reflectance curve here was the average value obtained in many sample points.…”

“…This is because green plants have strong absorption in the red (R) band and strong reflection in the NIR band. Some studies suggest that red edge and NIR bands are important in crop research [51,52]. However, it is worth mentioning that the value of the spectral reflectance curve here was the average value obtained in many sample points In the image, the actual reflectance value of each sample point fluctuated up and down In a particular band, the range of reflectance values for different crops overlapped.…”

Estimation of Intercepted Solar Radiation and Stem Water Potential in a Table Grape Vineyard Covered by Plastic Film Using Sentinel-2 Data: A Comparison of OLS-, MLR-, and ML-Based Methods

“…Reflectance in the visible and SWIR bands was found to be positively correlated with Ψstem, despite increasing reflectance in the SWIR range being commonly found to be strongly correlated with a decrease in leaf water content [79]. However, a negative slope value was also found for SWIR bands in a study conducted on cotton [80]; furthermore, in grapevines, it was found that the slope of the linear model relating Ψstem with B8a and B11 can be negative for Ψstem values > −0.70 MPa and positive for Ψstem < −0.90 MPa [81]. According to our results, Ψstem values lower than −0.90 MPa were found from DOY 201 (July 20) to DOY 234 (August 22, end of the field measurement); this corresponds, in the study area, to the typically warmer summer period.…”

Remote Sensing of Land Change: A Multifaceted Perspective

“…Remotely sensed data contain rich information on the characteristics of the land surface. A feature space of more than a few dozens to even hundreds of dimensions could be created from the electromagnetic radiation (EMR) that is recorded at different wavelengths, the texture of the spectral bands, and the intra-annual/inter-annual temporal trajectory from the time series observations, which could be further used to determine the land cover based on image classification (Gómez et al, 2016;Pouliot and Latifovic, 2016) or to estimate the biophysical/ biochemical parameters based on machine learning or regression from empirical models (Garbulsky et al, 2011;Lin et al, 2020;Verrelst et al, 2015). Recently, the deep-learning-based approaches, particularly Convolutional Neural Network (CNN), have shown better performance in land cover classification compared to the traditional machinelearning-based methods (Kussul et al, 2017;Liu et al, 2021b;Pouliot et al, 2021), and are capable of incorporating the spatial domain of the remote sensing data by automatically extracting a suitable representation of the remote sensing data through a hierarchy of spatial filters at different sizes, which avoids the feature creation and selection processes that most traditional machine learning methods require in advance for preparation of the classification predictors (Molinier et al, 2021).…”