scholarly journals Monitoring vineyard water status using Sentinel-2 images: qualitative survey on five wine estates in the south of France

OENO One ◽  
2021 ◽  
Vol 55 (4) ◽  
pp. 115-127
Author(s):  
Eve Laroche Pinel ◽  
Sylvie Duthoit ◽  
Anne D. Costard ◽  
Jacques Rousseau ◽  
Jérome Hourdel ◽  
...  
Keyword(s):  
Large Scale ◽  
Irrigation System ◽  
Water Status ◽  
Weather Forecast ◽  
Water Source ◽  
Wine Industry ◽  
Temporal Consistency ◽  
Stem Water Potential ◽  
The South ◽  
Sentinel 2

The wine industry must face many challenges because of climate change. One of them is the increase in temperatures and droughts events. These changes sometimes lead to yield losses and can also impact the quality of the wine produced (e.g., increased alcohol content). The management of available water is also a sensitive issue as water requirements for vineyard irrigation are quickly increasing in the south of France. In this context, there is a need for a decision tool that can help evaluate the vine water status through the entire growth season at a large scale. To address this issue, we have previously developed a model (see Laroche-Pinel et al. 2021a) which predicts the vine Stem Water Potential (Ψstem) using Sentinel-2 (S2) images. This model was developed based on a field campaign over three years. The present study now aims to investigate the feedback of winegrowers on the outputs of our model. Therefore, it was applied on the plots of five wine estates that do not belong to the set used in the initial paper. The qualitative results show interesting spatial and temporal consistency in accordance with winegrower knowledge, irrigation data, and weather forecast. The predicted Ψstemhighlights spatial variability in vine fields where a water source emerges and reflects the differences between vine fields with a drip or sparkling irrigation or without an irrigation system. The predicted Ψstem also clearly reacts to a peak in temperature. According to their feedback, three of the five winegrowers would be glad to use this service in the years to come.

scholarly journals Towards Vine Water Status Monitoring on a Large Scale Using Sentinel-2 Images

2021 ◽  
Vol 13 (9) ◽  
pp. 1837
Author(s):  
Eve Laroche-Pinel ◽  
Sylvie Duthoit ◽  
Mohanad Albughdadi ◽  
Anne D. Costard ◽  
Jacques Rousseau ◽  
...  
Keyword(s):  
Climate Change ◽  
Water Potential ◽  
Large Scale ◽  
Water Status ◽  
Vegetation Indices ◽  
Machine Learning Algorithms ◽  
Severe Drought ◽  
Stem Water Potential ◽  
Stem Water ◽  
Sentinel 2

Wine growing needs to adapt to confront climate change. In fact, the lack of water becomes more and more important in many regions. Whereas vineyards have been located in dry areas for decades, so they need special resilient varieties and/or a sufficient water supply at key development stages in case of severe drought. With climate change and the decrease of water availability, some vineyard regions face difficulties because of unsuitable variety, wrong vine management or due to the limited water access. Decision support tools are therefore required to optimize water use or to adapt agronomic practices. This study aimed at monitoring vine water status at a large scale with Sentinel-2 images. The goal was to provide a solution that would give spatialized and temporal information throughout the season on the water status of the vines. For this purpose, thirty six plots were monitored in total over three years (2018, 2019 and 2020). Vine water status was measured with stem water potential in field measurements from pea size to ripening stage. Simultaneously Sentinel-2 images were downloaded and processed to extract band reflectance values and compute vegetation indices. In our study, we tested five supervised regression machine learning algorithms to find possible relationships between stem water potential and data acquired from Sentinel-2 images (bands reflectance values and vegetation indices). Regression model using Red, NIR, Red-Edge and SWIR bands gave promising result to predict stem water potential (R2=0.40, RMSE=0.26).

Estimation water status of the vineyard by calculating multispectral index from satellite images

2021 ◽  
Author(s):  
Marta Rodríguez-Fernández ◽  
María Fandiño ◽  
Xesús Pablo González ◽  
Javier J. Cancela
Keyword(s):  
Water Stress ◽  
Water Potential ◽  
Spectral Index ◽  
Satellite Images ◽  
Irrigation System ◽  
Water Status ◽  
Stress Index ◽  
Stem Water Potential ◽  
Stem Water ◽  
Water Potential Measurements

<p>The estimation of the water status in the vineyard, is a very important factor, in which every day the winegrowers show more interest since it directly affects the quality and production in the vineyards. The situation generated by COVID-19 in viticulture, adds importance to tools that provide information of the hydric status of vineyard plants in a telematic way.</p><p>In the present study, the stem water potential in the 2018 and 2019 seasons, is analysed in a vineyard belonging to the Rias Baixas wine-growing area (Vilagarcia de Arousa, Spain), with 32 sampling points distributed throughout the plot, which allows the contrast and validation with the remote sensing methodology to estimate the water status of the vineyard using satellite images.</p><p>The satellite images have been downloaded from the Sentinel-2 satellite, on the closets available dates regarding the stem water potential measurements, carried out in the months of June to September, because this dates are considered the months in which vine plants have higher water requirements.</p><p>With satellite images, two spectral index related to the detection of water stress have been calculated: NDWI (Normalized Difference Water Index) and MSI (Moisture Stress Index). Stem water potential measurements, have allowed a linear regression with both index, to validate the use of these multispectral index to determine water stress in the vineyard.</p><p>Determination coefficients of r<sup>2</sup>=0.62 and 0.67, have been obtained in July and August 2018 and 0.54 in June of 2019 for the NDWI index, as well as values of 0.53 and 0.63 in July 2018 and June 2019 respectively, when it has been analysed the MSI index.</p><p>Between both seasons, the difference observed, that implies slightly greater water stress in 2019, is reflected in the climate conditions during the summer months, with an average accumulated rainfall that doesn’t exceed 46 mm of water. Although, the NDWI index has allowed to establish better relationships in the 2018 season respect to the MSI index and the 2019 season, (r<sup>2</sup>=0.60 NDWI in 2018), as well as greater differences in terms of water stress presented in the vineyard.</p><p>With the spectral index calculated, it has been possible to validate the use of these index for the determination of the water stress of the vineyard plants, as an efficient, fast and less expensive method, which allows the application of an efficient irrigation system in the vineyard.</p>

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

2020 ◽  
Vol 12 (7) ◽  
pp. 1176 ◽  
Author(s):  
Yukun Lin ◽  
Zhe Zhu ◽  
Wenxuan Guo ◽  
Yazhou Sun ◽  
Xiaoyuan Yang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Water Potential ◽  
Large Scale ◽  
Temporal Frequency ◽  
Vegetation Indices ◽  
Stem Water Potential ◽  
Spectral Bands ◽  
Red Edge ◽  
Sentinel 2

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 (R2 = 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 (R2 = 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.

Characterising essential breeding habitat for whales informs the development of large-scale Marine Protected Areas in the South Pacific

2016 ◽  
Vol 548 ◽  
pp. 263-275 ◽  
Author(s):  
RE Lindsay ◽  
R Constantine ◽  
J Robbins ◽  
DK Mattila ◽  
A Tagarino ◽  
...  
Keyword(s):  
Protected Areas ◽  
Marine Protected Areas ◽  
Large Scale ◽  
South Pacific ◽  
Breeding Habitat ◽  
The South

Swine Effluent for Tomato in a Plasticulture Production System

HortScience ◽  
1998 ◽  
Vol 33 (3) ◽  
pp. 524a-524 ◽  
Author(s):  
Kent Cushman ◽  
Thomas Horgan
Keyword(s):  
Production System ◽  
Irrigation System ◽  
Dry Weight ◽  
Water Source ◽  
Nutrient Concentrations ◽  
Plastic Mulch ◽  
Tomato Production ◽  
Swine Effluent ◽  
Soluble Fertilizer ◽  
Source Number

Tomato was grown in Fall 1997 with swine effluent or commercial soluble fertilizer in a plasticulture production system. Four cultivars, `Mountain Delight', `Celebrity', `Equinox', and `Sunbeam', were transplanted to raised beds with plastic mulch and drip irrigation. Preplant fertilizer was not applied. Effluent from the Wiley L. Bean Swine Demonstration Unit's secondary lagoon was filtered through in-line screen filters and applied directly to the plants through the irrigation system. Toward the end of each application, sodium hypochlorite was injected in the line to achieve a free chlorine concentration of ≈1%. Clogging of filters or drip emitters did not occur. Control plants received 100 ppm N from soluble fertilizer injected in irrigation lines supplied by a municipal water source. Number and weight of tomatoes from plants receiving swine effluent were equal to that of plants receiving soluble fertilizer. No differences in fruit quality were evident between treatments. Plant dry weight was also equal for three out of four cultivars. No differences in soil characteristics were detected between treatments after the study. Chemical analysis of the effluent showed a pH of 7.8 and nutrient concentrations of ≈110 ppm NH4-N, 57 ppm P2O5, 150 ppm K2O, and trace amounts of Cu and Zn. Though no differences in yield were detected in this study, the effluent's high pH and high NH4-N content need to be managed more closely for commercial tomato production.

MODELING THE SOUTH ATLANTIC OCEAN FROM MEDIUM TO HIGH RESOLUTION

2014 ◽  
Vol 31 (2) ◽  
Author(s):  
Mariela Gabioux ◽  
Vladimir Santos da Costa ◽  
Joao Marcos Azevedo Correia de Souza ◽  
Bruna Faria de Oliveira ◽  
Afonso De Moraes Paiva
Keyword(s):  
High Resolution ◽  
Atlantic Ocean ◽  
Large Scale ◽  
South Atlantic ◽  
Surface Relaxation ◽  
The South ◽  
Small Surface ◽  
Basic Model ◽  
Basic Set ◽  
Set Up

Results of the basic model configuration of the REMO project, a Brazilian approach towards operational oceanography, are discussed. This configuration consists basically of a high-resolution eddy-resolving, 1/12 degree model for the Metarea V, nested in a medium-resolution eddy-permitting, 1/4 degree model of the Atlantic Ocean. These simulations performed with HYCOM model, aim for: a) creating a basic set-up for implementation of assimilation techniques leading to ocean prediction; b) the development of hydrodynamics bases for environmental studies; c) providing boundary conditions for regional domains with increased resolution. The 1/4 degree simulation was able to simulate realistic equatorial and south Atlantic large scale circulation, both the wind-driven and the thermohaline components. The high resolution simulation was able to generate mesoscale and represent well the variability pattern within the Metarea V domain. The BC mean transport values were well represented in the southwestern region (between Vitória-Trinidade sea mount and 29S), in contrast to higher latitudes (higher than 30S) where it was slightly underestimated. Important issues for the simulation of the South Atlantic with high resolution are discussed, like the ideal place for boundaries, improvements in the bathymetric representation and the control of bias SST, by the introducing of a small surface relaxation. In order to make a preliminary assessment of the model behavior when submitted to data assimilation, the Cooper & Haines (1996) method was used to extrapolate SSH anomalies fields to deeper layers every 7 days, with encouraging results.

scholarly journals Uni-Temporal Multispectral Imagery for Burned Area Mapping with Deep Learning

2021 ◽  
Vol 13 (8) ◽  
pp. 1509
Author(s):  
Xikun Hu ◽  
Yifang Ban ◽  
Andrea Nascetti
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Multiple Scales ◽  
Detection Methods ◽  
Burned Area ◽  
Landsat 8 ◽  
Multispectral Imagery ◽  
Burned Areas ◽  
Local Climate Zones ◽  
Sentinel 2

Accurate burned area information is needed to assess the impacts of wildfires on people, communities, and natural ecosystems. Various burned area detection methods have been developed using satellite remote sensing measurements with wide coverage and frequent revisits. Our study aims to expound on the capability of deep learning (DL) models for automatically mapping burned areas from uni-temporal multispectral imagery. Specifically, several semantic segmentation network architectures, i.e., U-Net, HRNet, Fast-SCNN, and DeepLabv3+, and machine learning (ML) algorithms were applied to Sentinel-2 imagery and Landsat-8 imagery in three wildfire sites in two different local climate zones. The validation results show that the DL algorithms outperform the ML methods in two of the three cases with the compact burned scars, while ML methods seem to be more suitable for mapping dispersed burn in boreal forests. Using Sentinel-2 images, U-Net and HRNet exhibit comparatively identical performance with higher kappa (around 0.9) in one heterogeneous Mediterranean fire site in Greece; Fast-SCNN performs better than others with kappa over 0.79 in one compact boreal forest fire with various burn severity in Sweden. Furthermore, directly transferring the trained models to corresponding Landsat-8 data, HRNet dominates in the three test sites among DL models and can preserve the high accuracy. The results demonstrated that DL models can make full use of contextual information and capture spatial details in multiple scales from fire-sensitive spectral bands to map burned areas. Using only a post-fire image, the DL methods not only provide automatic, accurate, and bias-free large-scale mapping option with cross-sensor applicability, but also have potential to be used for onboard processing in the next Earth observation satellites.

scholarly journals Enhancement of Detecting Permanent Water and Temporary Water in Flood Disasters by Fusing Sentinel-1 and Sentinel-2 Imagery Using Deep Learning Algorithms: Demonstration of Sen1Floods11 Benchmark Datasets

2021 ◽  
Vol 13 (11) ◽  
pp. 2220
Author(s):  
Yanbing Bai ◽  
Wenqi Wu ◽  
Zhengxin Yang ◽  
Jinze Yu ◽  
Bo Zhao ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Large Scale ◽  
Learning Algorithms ◽  
Flood Events ◽  
Test Set ◽  
Source Data ◽  
Flood Disasters ◽  
Temporary Water ◽  
Sentinel 2

Identifying permanent water and temporary water in flood disasters efficiently has mainly relied on change detection method from multi-temporal remote sensing imageries, but estimating the water type in flood disaster events from only post-flood remote sensing imageries still remains challenging. Research progress in recent years has demonstrated the excellent potential of multi-source data fusion and deep learning algorithms in improving flood detection, while this field has only been studied initially due to the lack of large-scale labelled remote sensing images of flood events. Here, we present new deep learning algorithms and a multi-source data fusion driven flood inundation mapping approach by leveraging a large-scale publicly available Sen1Flood11 dataset consisting of roughly 4831 labelled Sentinel-1 SAR and Sentinel-2 optical imagery gathered from flood events worldwide in recent years. Specifically, we proposed an automatic segmentation method for surface water, permanent water, and temporary water identification, and all tasks share the same convolutional neural network architecture. We utilize focal loss to deal with the class (water/non-water) imbalance problem. Thorough ablation experiments and analysis confirmed the effectiveness of various proposed designs. In comparison experiments, the method proposed in this paper is superior to other classical models. Our model achieves a mean Intersection over Union (mIoU) of 52.99%, Intersection over Union (IoU) of 52.30%, and Overall Accuracy (OA) of 92.81% on the Sen1Flood11 test set. On the Sen1Flood11 Bolivia test set, our model also achieves very high mIoU (47.88%), IoU (76.74%), and OA (95.59%) and shows good generalization ability.

Sign in / Sign up

Export Citation Format

Share Document