Modelling Water Stress in a Shiraz Vineyard Using Hyperspectral Imaging and Machine Learning

Loggenberg, Kyle; Strever, A.E.; Greyling, Berno Theo; Poona, Nitesh

doi:10.3390/rs10020202

Cited by 103 publications

(72 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…High-resolution thermal imagery obtained from a hyperspectral scanner was used to map canopy stomatal conductance (g s ) and CWSI of olive orchards where different irrigation treatments were applied [18]. With the large volume of spatial/spectral data extracted from the hyperspectral data cube, machine learning will likely be adopted more widely in the horticultural environment to model water stress [141]. See Reference [54] for a comprehensive review of hyperspectral and thermal remote sensing to detect plant water status.…”

Section: Hyperspectralmentioning

confidence: 99%

“…These variables can include spectral response, thermal response, meteorological data, 3D attributes of the canopy, and macrostructure of the block (farm). Clearly, there is an opportunity for a multi-disciplinary approach, potentially incorporating artificial intelligence techniques which incorporate the aforementioned variables to provide a robust estimation of crop water status [84,141,282,302,303]. Furthermore, with machine learning algorithms, hyperspectral remote sensing will provide a wealth of data to estimate crop water status.…”

Section: Future Prospective and Gaps In The Knowledgementioning

confidence: 99%

See 1 more Smart Citation

A Review of Current and Potential Applications of Remote Sensing to Study the Water Status of Horticultural Crops

Gautam

Pagay

2020

Agronomy

View full text Add to dashboard Cite

With increasingly advanced remote sensing systems, more accurate retrievals of crop water status are being made at the individual crop level to aid in precision irrigation. This paper summarises the use of remote sensing for the estimation of water status in horticultural crops. The remote measurements of the water potential, soil moisture, evapotranspiration, canopy 3D structure, and vigour for water status estimation are presented in this comprehensive review. These parameters directly or indirectly provide estimates of crop water status, which is critically important for irrigation management in farms. The review is organised into four main sections: (i) remote sensing platforms; (ii) the remote sensor suite; (iii) techniques adopted for horticultural applications and indicators of water status; and, (iv) case studies of the use of remote sensing in horticultural crops. Finally, the authors' view is presented with regard to future prospects and research gaps in the estimation of the crop water status for precision irrigation.

show abstract

Section: Hyperspectralmentioning

confidence: 99%

Section: Future Prospective and Gaps In The Knowledgementioning

confidence: 99%

A Review of Current and Potential Applications of Remote Sensing to Study the Water Status of Horticultural Crops

Gautam

Pagay

2020

Agronomy

View full text Add to dashboard Cite

show abstract

“…Thus it makes XGBoost even faster than RF. Recently, it has been popular in many classification and crop mapping applications [39][40][41][42][43]. Considering the intensive computation requirements in sugarcane mapping utilizing different polarizations and random split sample sets, we chose the time efficiency algorithms including RF and XGBoost as classifiers and evaluated their performance.…”

Section: Feature Importance Evaluationmentioning

confidence: 99%

Early Season Mapping of Sugarcane by Applying Machine Learning Algorithms to Sentinel-1A/2 Time Series Data: A Case Study in Zhanjiang City, China

Jiang

Jing

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

More than 90% of the sugar production in China comes from sugarcane, which is widely grown in South China. Optical image time series have proven to be efficient for sugarcane mapping. There are, however, two limitations associated with previous research: one is that the critical observations during the sugarcane growing season are limited due to frequent cloudy weather in South China; the other is that the classification method requires imagery time series covering the entire growing season, which reduces the time efficiency. The Sentinel-1A (S1A) synthetic aperture radar (SAR) data featuring relatively high spatial-temporal resolution provides an ideal data source for all-weather observations. In this study, we attempted to develop a method for the early season mapping of sugarcane. First, we proposed a framework consisting of two procedures: initial sugarcane mapping using the S1A SAR imagery time series, followed by non-vegetation removal using Sentinel-2 optical imagery. Second, we tested the framework using an incremental classification strategy based on S1A imagery covering the entire 2017–2018 sugarcane season. The study area was in Suixi and Leizhou counties of Zhanjiang city, China. Results indicated that an acceptable accuracy, in terms of Kappa coefficient, can be achieved to a level above 0.902 using time series three months before sugarcane harvest. In general, sugarcane mapping utilizing the combination of VH + VV as well as VH polarization alone outperformed mapping using VV alone. Although the XGBoost classifier with VH + VV polarization achieved a maximum accuracy that was slightly lower than the random forest (RF) classifier, the XGBoost shows promising performance in that it was more robust to overfitting with noisy VV time series and the computation speed was 7.7 times faster than RF classifier. The total sugarcane areas in Suixi and Leizhou for the 2017–2018 harvest year estimated by this study were approximately 598.95 km2 and 497.65 km2, respectively. The relative accuracy of the total sugarcane mapping area was approximately 86.3%.

show abstract

“…Here, we describe the modified version of DoTRules for hyperspectral image classification, before demonstrating its application in three different study areas. We quantify the accuracy of DoTRules for hyperspectral image classification, and compare the results against some popular state-of-the-art ensemble approaches, i.e., extreme gradient boosting (XGBoost) [40,41], random forest (RF) [1,[42][43][44][45], rotation forests (RoFs) [46][47][48][49], regularised random forest (RRF) [50,51], as well as two non-ensemble algorithms, namely, support vector machine (SVM) [52][53][54][55][56], and deep belief network (DBN) [57,58] as the classic deep learning method. Although SVM and DBN are not ensemble methods, they are included in our comparison because of their popularity, as they have been repeatedly used in recent hyperspectral image classification studies using Indian Pines, Salinas and Pavia University datasets.…”

Section: Introductionmentioning

confidence: 99%

A Robust Rule-Based Ensemble Framework Using Mean-Shift Segmentation for Hyperspectral Image Classification

et al. 2019

View full text Add to dashboard Cite

This paper assesses the performance of DoTRules-a dictionary of trusted rules-as a supervised rule-based ensemble framework based on the mean-shift segmentation for hyperspectral image classification. The proposed ensemble framework consists of multiple rule sets with rules constructed based on different class frequencies and sequences of occurrences. Shannon entropy was derived for assessing the uncertainty of every rule and the subsequent filtering of unreliable rules. DoTRules is not only a transparent approach for image classification but also a tool to map rule uncertainty, where rule uncertainty assessment can be applied as an estimate of classification accuracy prior to image classification. In this research, the proposed image classification framework is implemented using three world reference hyperspectral image datasets. We found that the overall accuracy of classification using the proposed ensemble framework was superior to state-of-the-art ensemble algorithms, as well as two non-ensemble algorithms, at multiple training sample sizes. We believe DoTRules can be applied more generally to the classification of discrete data such as hyperspectral satellite imagery products.Bayesian [17], maximum margin [18], evolutionary [19], clustering [9], association rule learning [20], artificial neural network [12,21,22] and deep learning [23] methods (see Figure 1). Regardless of the classification performance, many of these algorithms act as black-boxes, resulting in a poor recognition of the classification structure and robustness owing to the high-dimensionality of the data [24,25].

show abstract

Modelling Water Stress in a Shiraz Vineyard Using Hyperspectral Imaging and Machine Learning

Cited by 103 publications

References 56 publications

A Review of Current and Potential Applications of Remote Sensing to Study the Water Status of Horticultural Crops

A Review of Current and Potential Applications of Remote Sensing to Study the Water Status of Horticultural Crops

Early Season Mapping of Sugarcane by Applying Machine Learning Algorithms to Sentinel-1A/2 Time Series Data: A Case Study in Zhanjiang City, China

A Robust Rule-Based Ensemble Framework Using Mean-Shift Segmentation for Hyperspectral Image Classification

Contact Info

Product

Resources

About