Color Calibration of Proximal Sensing RGB Images of Oilseed Rape Canopy via Deep Learning Combined with K-Means Algorithm

Advances in optical phenotyping of cereal crops

Optical sensors and sensing-based phenotyping techniques have become mainstream approaches in high-throughput phenotyping for improving trait selection and genetic gains in crops. We review recent progress and contemporary applications of optical sensing-based phenotyping (OSP) techniques in cereal crops and highlight optical sensing principles for spectral response and sensor specifications. Further, we group phenotypic traits determined by OSP into four categories - morphological, biochemical, physiological, and performance traits - and illustrate appropriate sensors for each extraction. In addition to the current status, we discuss the challenges of OSP and provide possible solutions. We propose that optical sensing-based traits need to be explored further, and that standardization of the language of phenotyping and worldwide collaboration between phenotyping researchers and other fields need to be established.

Developing and Testing a Deep Learning Approach for Mapping Retrogressive Thaw Slumps

In a warming Arctic, permafrost-related disturbances, such as retrogressive thaw slumps (RTS), are becoming more abundant and dynamic, with serious implications for permafrost stability and bio-geochemical cycles on local to regional scales. Despite recent advances in the field of earth observation, many of these have remained undetected as RTS are highly dynamic, small, and scattered across the remote permafrost region. Here, we assessed the potential strengths and limitations of using deep learning for the automatic segmentation of RTS using PlanetScope satellite imagery, ArcticDEM and auxiliary datasets. We analyzed the transferability and potential for pan-Arctic upscaling and regional cross-validation, with independent training and validation regions, in six different thaw slump-affected regions in Canada and Russia. We further tested state-of-the-art model architectures (UNet, UNet++, DeepLabv3) and encoder networks to find optimal model configurations for potential upscaling to continental scales. The best deep learning models achieved mixed results from good to very good agreement in four of the six regions (maxIoU: 0.39 to 0.58; Lena River, Horton Delta, Herschel Island, Kolguev Island), while they failed in two regions (Banks Island, Tuktoyaktuk). Of the tested architectures, UNet++ performed the best. The large variance in regional performance highlights the requirement for a sufficient quantity, quality and spatial variability in the training data used for segmenting RTS across diverse permafrost landscapes, in varying environmental conditions. With our highly automated and configurable workflow, we see great potential for the transfer to active RTS clusters (e.g., Peel Plateau) and upscaling to much larger regions.

Gradient Boosting Machine and Object-Based CNN for Land Cover Classification

In regular convolutional neural networks (CNN), fully-connected layers act as classifiers to estimate the probabilities for each instance in classification tasks. The accuracy of CNNs can be improved by replacing fully connected layers with gradient boosting algorithms. In this regard, this study investigates three robust classifiers, namely XGBoost, LightGBM, and Catboost, in combination with a CNN for a land cover study in Hanoi, Vietnam. The experiments were implemented using SPOT7 imagery through (1) image segmentation and extraction of features, including spectral information and spatial metrics, (2) normalization of attribute values and generation of graphs, and (3) using graphs as the input dataset to the investigated models for classifying six land cover classes, namely House, Bare land, Vegetation, Water, Impervious Surface, and Shadow. The results show that CNN-based XGBoost (Overall accuracy = 0.8905), LightGBM (0.8956), and CatBoost (0.8956) outperform the other methods used for comparison. It can be seen that the combination of object-based image analysis and CNN-based gradient boosting algorithms significantly improves classification accuracies and can be considered as alternative methods for land cover analysis.

Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies—Part 1: Literature Review

Convolutional neural network (CNN)-based deep learning (DL) is a powerful, recently developed image classification approach. With origins in the computer vision and image processing communities, the accuracy assessment methods developed for CNN-based DL use a wide range of metrics that may be unfamiliar to the remote sensing (RS) community. To explore the differences between traditional RS and DL RS methods, we surveyed a random selection of 100 papers from the RS DL literature. The results show that RS DL studies have largely abandoned traditional RS accuracy assessment terminology, though some of the accuracy measures typically used in DL papers, most notably precision and recall, have direct equivalents in traditional RS terminology. Some of the DL accuracy terms have multiple names, or are equivalent to another measure. In our sample, DL studies only rarely reported a complete confusion matrix, and when they did so, it was even more rare that the confusion matrix estimated population properties. On the other hand, some DL studies are increasingly paying attention to the role of class prevalence in designing accuracy assessment approaches. DL studies that evaluate the decision boundary threshold over a range of values tend to use the precision-recall (P-R) curve, the associated area under the curve (AUC) measures of average precision (AP) and mean average precision (mAP), rather than the traditional receiver operating characteristic (ROC) curve and its AUC. DL studies are also notable for testing the generalization of their models on entirely new datasets, including data from new areas, new acquisition times, or even new sensors.

Selecting Optimal Combination of Data Channels for Semantic Segmentation in City Information Modelling (CIM)

Over the last decade, a 3D reconstruction technique has been developed to present the latest as-is information for various objects and build the city information models. Meanwhile, deep learning based approaches are employed to add semantic information to the models. Studies have proved that the accuracy of the model could be improved by combining multiple data channels (e.g., XYZ, Intensity, D, and RGB). Nevertheless, the redundant data channels in large-scale datasets may cause high computation cost and time during data processing. Few researchers have addressed the question of which combination of channels is optimal in terms of overall accuracy (OA) and mean intersection over union (mIoU). Therefore, a framework is proposed to explore an efficient data fusion approach for semantic segmentation by selecting an optimal combination of data channels. In the framework, a total of 13 channel combinations are investigated to pre-process data and the encoder-to-decoder structure is utilized for network permutations. A case study is carried out to investigate the efficiency of the proposed approach by adopting a city-level benchmark dataset and applying nine networks. It is found that the combination of IRGB channels provide the best OA performance, while IRGBD channels provide the best mIoU performance.

The role of clustering algorithm-based big data processing in information economy development

The purposes are to evaluate the Distributed Clustering Algorithm (DCA) applicability in the power system's big data processing and find the information economic dispatch strategy suitable for new energy consumption in power systems. A two-layer DCA algorithm is proposed based on K-Means Clustering (KMC) and Affinity Propagation (AP) clustering algorithms. Then the incentive Demand Response (DR) is introduced, and the DR flexibility of the user side is analyzed. Finally, the day-ahead dispatch and real-time dispatch schemes are combined, and a multi-period information economic dispatch model is constructed. The algorithm performance is analyzed according to case analyses of new energy consumption. Results demonstrate that the two-layer DCA's calculation time is 5.23s only, the number of iterations is small, and the classification accuracy rate reaches 0.991. Case 2 corresponding to the proposed model can consume the new energy, and the income of the aggregator can be maximized. In short, the multi-period information economic dispatch model can consume the new energy and meet the DR of the user side.

Oil Spill Detection Using LBP Feature and K-Means Clustering in Shipborne Radar Image

Oil spill accidents have seriously harmed the marine environment. Effective oil spill monitoring can provide strong scientific and technological support for emergency response of law enforcement departments. Shipborne radar can be used to monitor oil spills immediately after the accident. In this paper, the original shipborne radar image collected by the teaching-practice ship Yukun of Dalian Maritime University during the oil spill accident of Dalian on 16 July 2010 was taken as the research data, and an oil spill detection method was proposed by using LBP texture feature and K-means algorithm. First, Laplacian operator, Otsu algorithm, and mean filter were used to suppress the co-frequency interference noises and high brightness pixels. Then the gray intensity correction matrix was used to reduce image nonuniformity. Next, using LBP texture feature and K-means clustering algorithm, the effective oil spill regions were extracted. Finally, the adaptive threshold was applied to identify the oil films. This method can automatically detect oil spills in shipborne radar image. It can provide a guarantee for real-time monitoring of oil spill accidents.