Automatic detection and removal of weeds is a challenging task that requires precise sensors. While crops and weeds possess similar features in terms of appearance, they can be discriminated based on spectral information. This can be done because any object has its own specific spectral signature based on its physical structure and chemical contents. This study examined the use of wavelet transform and deep learning for discrimination of weeds from crops. A total of 626 spectral reflectances in the range of 380 to 1,000 nm were obtained for three crops (cucumber [Cucumis sativus L.], tomato [Solanum lycopersicum L.], and bell pepper [Capsicum annuum L.]) and five different weeds (bindweed [Convolvulus spp.], purple nutsedge [Cyperus rotundus L.], narrowleaf plantain [Plantago lanceolata L.], common cinquefoil [Potentilla simplex Michx.], and garden sorrel [Rumex acetosa L.]). Morse wavelet was employed to decompose the spectra and extract the scalograms, which are the RGB representations of the spectral data. Two deep convolutional neural networks (i.e., GoogLeNet and SqueezNet) were employed for the recognition of crops and weeds. In addition, six common classifiers, including linear discriminant analysis, quadratic discriminant analysis, linear support vector machine, quadratic support vector machine, artificial neural networks, and k-nearest neighbors classifier (KNN), were used for the task of crop/weed discrimination to build the comparison with the proposed method. The error of prediction gradually decreased, and a 100% correct classification was achieved after 258 iterations. Analysis showed that SqueezNet provided classification of 100% accuracy, while GoogLeNet’s accuracy was 97.8% for the test set. Among the common classifiers, KNN provided the highest accuracy (i.e., 100%). This study showed that the proposed method can be successfully utilized for classification of crops and weeds.

New advancements in radio data post-processing are underway within the Square Kilometre Array (SKA) precursor community, aiming to facilitate the extraction of scientific results from survey images through a semi-automated approach. Several of these developments leverage deep learning methodologies for diverse tasks, including source detection, object or morphology classification, and anomaly detection. Despite substantial progress, the full potential of these methods often remains untapped due to challenges associated with training large supervised models, particularly in the presence of small and class-unbalanced labelled datasets.

Self-supervised learning has recently established itself as a powerful methodology to deal with some of the aforementioned challenges, by directly learning a lower-dimensional representation from large samples of unlabelled data. The resulting model and data representation can then be used for data inspection and various downstream tasks if a small subset of labelled data is available.

In this work, we explored contrastive learning methods to learn suitable radio data representations by training the SimCLR model on large collections of unlabelled radio images taken from the ASKAP EMU and SARAO MeerKAT GPS surveys. The resulting models were fine-tuned over smaller labelled datasets, including annotated images from various radio surveys, and evaluated on radio source detection and classification tasks. Additionally, we employed the trained self-supervised models to extract features from radio images, which were used in an unsupervised search for objects with peculiar morphology in the ASKAP EMU pilot survey data. For all considered downstream tasks, we reported the model performance metrics and discussed the benefits brought by self-supervised pre-training, paving the way for building radio foundational models in the SKA era.

Commentary of ‘Elemental psychopathology: distilling constituent symptoms and patterns of repetition in the diagnostic criteria of the DSM-5’ Vincent P. Martin 1, Régis Lopez 2,3, Jean-Arthur Micoulaud-Franchi 4,5, Christophe Gauld 4,6,*

Recent conceptualisations of bilingualism are moving away from strict categorisations, towards continuous approaches. This study supports this trend by combining empirical psycholinguistics data with machine learning classification modelling. Support vector classifiers were trained on two datasets of coded productions by Italian speakers to predict the class they belonged to (“monolingual”, “attriters” and “heritage”). All classes can be predicted above chance (>33%), even if the classifier's performance substantially varies, with monolinguals identified much better (f-score >70%) than attriters (f-score <50%), which are instead the most confusable class. Further analyses of the classification errors expressed in the confusion matrices qualify that attriters are identified as heritage speakers nearly as often as they are correctly classified. Cluster clitics are the most identifying features for the classification performance. Overall, this study supports a conceptualisation of bilingualism as a continuum of linguistic behaviours rather than sets of a priori established classes.

We present a fully-automated workflow to map sea ice types from Sentinel-1 data and transfer the results in near real-time to the research vessel Kronprins Haakon (KPH) in order to support tactical navigation and decision-making during a research cruise conducted towards Belgica Bank in April and May 2022. We used overlapping SAR and optical imagery to train a pixel-wise classifier for the required season and region, and implemented a processing chain with the Norwegian Ice Service at MET Norway that automatically classifies all Sentinel-1 images covering the area of interest. During the cruise, classification results were available on KPH within hours after image acquisition, which is significantly faster than manually produced ice charts. We evaluate the results both quantitatively, based on manually selected validation regions, and qualitatively in comparison to in-situ observations and photographs. Our findings show that open water, level ice, and deformed ice are classified with high accuracy, while young ice remains challenging due to its variable small-scale surface roughness. This work presents one of the first attempts to transfer automated ice type classification results into the field in near real-time and contributes to bridging the gap between research and operations in automated sea ice mapping.

A Microsoft® Visual Basic software, WinClbclas, has been developed to calculate the chemical formulae of columbite-supergroup minerals based on data obtained from wet-chemical and electron-microprobe analyses and using the current nomenclature scheme adopted by the Commission on New Minerals, Nomenclature and Classification (CNMNC) of the International Mineralogical Association (IMA) for columbite-supergroup minerals. The program evaluates 36 IMA-approved species, three questionable in terms of their unit-cell parameters, four insufficiently studied questionable species and one ungrouped species, all according to the dominant valance and constituent status in five mineral groups including ixiolite (MO2), wolframite (M1M2O4), samarskite (ABM2O8), columbite (M1M2O6) and wodginite (M1M2M32O8). Mineral compositions of the columbite supergroup are calculated on the basis of 24 oxygen atoms per formula unit. However, the formulae of the five ixiolite to wodginite groups can be estimated by the program on the basis of their cation and anion values in their typical mineral formulae (e.g. 4 cations and 8 oxygens for the wodginite group) with normalisation procedures. The Fe3+ and Fe2+ contents from microprobe-derived total FeO (wt.%) amounts are estimated by stoichiometric constraints. WinClbclas allows users to: (1) enter up to 47 input variables for mineral compositions; (2) type and load multiple columbite-supergroup mineral compositions in the data entry section; (3) edit and load the Microsoft® Excel files used in calculating, classifying, and naming the columbite-supergroup minerals, together with the total monovalent to hexavalent ion; and (4) store all the calculated parameters in the output of a Microsoft® Excel file for further data evaluation. The program is distributed as a self-extracting setup file, including the necessary support files used by the program, a help file and representative sample data files.

This paper provides a new classification of Central–Southern Italian dialects using dialectometric methods. All varieties considered are analyzed and cast in a data set where homogeneous areas are evaluated according to a selected list of phonetic features. Using numerical evaluation of these features and the Manhattan distance, a linguistic distance rule is defined. On this basis, the classification problem is formulated as a clustering problem, and a k-means algorithm is used. Additionally, an ad-hoc rule is set to identify transitional areas, and silhouette analysis is used to select the most appropriate number of clusters. While meaningful results are obtained for each number of clusters, a nine-group classification emerges as the most appropriate. As the results suggest, this classification is less subjective, more precise, and more comprehensive than traditional ones based on selected isoglosses.

The diagnosis of cystic echinococcosis (CE) is based on imaging. Detection of a focal lesion with morphological characteristics of Echinococcus granulosus sensu lato metacestode is the starting point for the diagnostic workup. In organs explorable with ultrasound (US), this is the method of choice for both aetiological diagnosis of CE and staging of the CE cyst. Staging in terms of lesion morphology is also needed when serology is added to the diagnostic workflow when imaging alone is inconclusive. Finally, staging guides the clinical management of uncomplicated CE, especially in the liver. This commentary provides an overview of the most up-to-date evidence backing the above-mentioned role of US in the diagnosis and clinical management of CE. Finally, we outline future perspectives for the improvement of CE diagnosis.