Search

To solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross validation (RFECV) algorithm and time convolution network–efficient channel attention mechanism–long short-term memory network (TCN–ECA–LSTM) is presented. First, the load sequence is decomposed into a relatively stable set of modal components using variational mode decomposition. Then, the RFECV-based method filters the feature set of each modal component to construct the best feature set. Finally, a two-stage prediction model based on TCN–ECA–LSTM is established. The first stage predicts each modal component and the second stage reconstructs the load forecast based on the predicted value of the previous stage. This paper takes actual data from New South Wales, Australia, as an example, and the results show that the method proposed in this paper can build the feature set reliably and efficiently and has a higher accuracy than the conventional prediction model. [ABSTRACT FROM AUTHOR]

Simple Summary: In radiotherapy treatment, organs at risk and target volumes are contoured by the clinicians to prepare a dosimetry plan. In retrospective data, these structures are not often standardised to universal names across the patients plans, which is required to enable data mining and analysis. In this paper, a new method was proposed and evaluated to automatically standardise radiotherapy structures names using machine learning algorithms. The proposed approach was deployed over a dataset with 1613 patients collected from Liverpool & Macarthur Cancer Therapy Centres, New South Wales, Australia. It was concluded that machine learning techniques can standardise the dosimetry plan structures, taking into consideration the integration of multiple modalities representing each structure during the training process. In progressing the use of big data in health systems, standardised nomenclature is required to enable data pooling and analyses. In many radiotherapy planning systems and their data archives, target volumes (TV) and organ-at-risk (OAR) structure nomenclature has not been standardised. Machine learning (ML) has been utilised to standardise volumes nomenclature in retrospective datasets. However, only subsets of the structures have been targeted. Within this paper, we proposed a new approach for standardising all the structures nomenclature by using multi-modal artificial neural networks. A cohort consisting of 1613 breast cancer patients treated with radiotherapy was identified from Liverpool & Macarthur Cancer Therapy Centres, NSW, Australia. Four types of volume characteristics were generated to represent each target and OAR volume: textual features, geometric features, dosimetry features, and imaging data. Five datasets were created from the original cohort, the first four represented different subsets of volumes and the last one represented the whole list of volumes. For each dataset, 15 sets of combinations of features were generated to investigate the effect of using different characteristics on the standardisation performance. The best model reported 99.416% classification accuracy over the hold-out sample when used to standardise all the nomenclatures in a breast cancer radiotherapy plan into 21 classes. Our results showed that ML based automation methods can be used for standardising naming conventions in a radiotherapy plan taking into consideration the inclusion of multiple modalities to better represent each volume. [ABSTRACT FROM AUTHOR]

Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas. Exploiting this data is presently limited by the time it takes for experts to identify organisms found in these images. With this limitation in mind, a large effort has been made globally to introduce automation and machine learning algorithms to accelerate both classification and assessment of marine benthic biota. One major issue lies with organisms that move with swell and currents, such as kelps. This paper presents an automatic hierarchical classification method local binary classification as opposed to the conventional flat classification to classify kelps in images collected by autonomous underwater vehicles. The proposed kelp classification approach exploits learned feature representations extracted from deep residual networks. We show that these generic features outperform the traditional off-the-shelf CNN features and the conventional hand-crafted features. Experiments also demonstrate that the hierarchical classification method outperforms the traditional parallel multi-class classifications by a significant margin (90.0% vs. 57.6% and 77.2% vs. 59.0%) on Benthoz15 and Rottnest datasets respectively. Furthermore, we compare different hierarchical classification approaches and experimentally show that the sibling hierarchical training approach outperforms the inclusive hierarchical approach by a significant margin. We also report an application of our proposed method to study the change in kelp cover over time for annually repeated AUV surveys.

To increase data availability and accuracy in the coastal zone, especially in the last 5 km to the coast, we present a SCMR (Seamless Combination of Multiple Retrackers) processing strategy to combine sea surface height (SSH) estimates from waveform retrackers of SGDR MLE4, ALES, WLS3 and MB4 for Jason-3 and Saral missions, and of SAMOSA and SAMOSA+ for Sentinel-3A mission in the Australian coastal zone. The SCMR does not require the waveform classification result. It includes two steps: (1) estimating and removing the SSH bias due mainly to the significant wave height (SWH) difference-dependent height differences, and (2) determining the optimal along-track SSH profile by using the Dijkstra algorithm. In the study region, the results show that the SCMR increases the data availability by up to 15% in the last 5 km to the coast and reduces the noise level by 28–34% at the spatial scales < 2.5 km. The validation results against tide gauges show that SCMR-derived SSH estimates achieve a better accuracy than that from any single retracker, with the improvement percentage of 6.26% and 4.94% over 0–10 km and 20–100 km distance bands, respectively. [ABSTRACT FROM AUTHOR]

Regional flood frequency analysis (RFFA) is widely used to estimate design floods in ungauged catchments. Both linear and non-linear methods are adopted in RFFA. The development of the non-linear RFFA method Adaptive Neuro-fuzzy Inference System (ANFIS) using data from 181 gauged catchments in south-eastern Australia is presented in this study. Three different types of ANFIS models, Fuzzy C-mean (FCM), Subtractive Clustering (SC), and Grid Partitioning (GP) were adopted, and the results were compared with the Quantile Regression Technique (QRT). It was found that FCM performs better (with relative error (RE) values in the range of 38–60%) than the SC (RE of 44–69%) and GP (RE of 42–78%) models. The FCM performs better for smaller to medium ARIs (2 to 20 years) (ARI of five years having the best performance), and in New South Wales, over Victoria. In many aspects, the QRT and FCM models perform very similarly. These developed RFFA models can be used in south-eastern Australia to derive more accurate flood quantiles. The developed method can easily be adapted to other parts of Australia and other countries. The results of this study will assist in updating the Australian Rainfall Runoff (national guide)-recommended RFFA technique. [ABSTRACT FROM AUTHOR]

An atmospheric correction algorithm for medium-resolution satellite data over general water surfaces (open/coastal, estuarine and inland waters) has been assessed in Australian coastal waters. In situ measurements at four match-up sites were used with 21 Landsat 8 images acquired between 2014 and 2017. Three aerosol sources (AERONET, MODIS ocean aerosol and climatology) were used to test the impact of the selection of aerosol optical depth (AOD) and Ångström coefficient on the retrieved accuracy. The initial results showed that the satellite-derived water-leaving reflectance can have good agreement with the in situ measurements, provided that the sun glint is handled effectively. Although the AERONET aerosol data performed best, the contemporary satellite-derived aerosol information from MODIS or an aerosol climatology could also be as effective, and should be assessed with further in situ measurements. Two sun glint correction strategies were assessed for their ability to remove the glint bias. The most successful one used the average of two shortwave infrared (SWIR) bands to represent sun glint and subtracted it from each band. Using this sun glint correction method, the mean all-band error of the retrieved water-leaving reflectance at the Lucinda Jetty Coastal Observatory (LJCO) in north east Australia was close to 4% and unbiased over 14 acquisitions. A persistent bias in the other strategy was likely due to the sky radiance being non-uniform for the selected images. In regard to future options for an operational sun glint correction, the simple method may be sufficient for clear skies until a physically based method has been established. [ABSTRACT FROM AUTHOR]

In this study we present the retrieval of the column-averaged dry air mole fraction of carbon dioxide (XCO2) from the TanSat observations using the ACOS (Atmospheric CO2 Observations from Space) algorithm. The XCO2 product has been validated with collocated ground-based measurements from the Total Carbon Column Observing Network (TCCON) for 2 years of TanSat data from 2017 to 2018. Based on the correlation of the XCO2 error over land with goodness of fit in three spectral bands at 0.76, 1.61 and 2.06 μm, we applied an a posteriori bias correction to TanSat retrievals. For overpass averaged results, XCO2 retrievals show a standard deviation (SD) of ~2.45 ppm and a positive bias of ~0.27 ppm compared to collocated TCCON sites. The validation also shows a relatively higher positive bias and variance against TCCON over high-latitude regions. Three cases to evaluate TanSat target mode retrievals are investigated, including one field campaign at Dunhuang with measurements by a greenhouse gas analyzer deployed on an unmanned aerial vehicle and two cases with measurements by a ground-based Fourier-transform spectrometer in Beijing. The results show the retrievals of all footprints, except footprint-6, have relatively low bias (within ~2 ppm). In addition, the orbital XCO2 distributions over Australia and Northeast China between TanSat and the second Orbiting Carbon Observatory (OCO-2) on 20 April 2017 are compared. It shows that the mean XCO2 from TanSat is slightly lower than that of OCO-2 with an average difference of ~0.85 ppm. A reasonable agreement in XCO2 distribution is found over Australia and Northeast China between TanSat and OCO-2. [ABSTRACT FROM AUTHOR]