Classification of catchments for nitrogen using Artificial Neural Network Pattern Recognition and spatial data

Explainable AI approach with original vegetation data classifies spatio-temporal nitrogen in flows from ungauged catchments to the Great Barrier Reef

Transfer of processed data and parameters to ungauged catchments from the most similar gauged counterpart is a common technique in water quality modelling. But catchment similarities for Dissolved Inorganic Nitrogen (DIN) are ill posed, which affects the predictive capability of models reliant on such methods for simulating DIN. Spatial data proxies to classify catchments for most similar DIN responses are a demonstrated solution, yet their applicability to ungauged catchments is unexplored. We adopted a neural network pattern recognition model (ANN-PR) and explainable artificial intelligence approach (SHAP-XAI) to match all ungauged catchments that flow to the Great Barrier Reef to gauged ones based on proxy spatial data. Catchment match suitability was verified using a neural network water quality (ANN-WQ) simulator trained on gauged catchment datasets, tested by simulating DIN for matched catchments in unsupervised learning scenarios. We show that discriminating training data to DIN regime benefits ANN-WQ simulation performance in unsupervised scenarios ( p< 0.05). This phenomenon demonstrates that proxy spatial data is a useful tool to classify catchments with similar DIN regimes. Catchments lacking similarity with gauged ones are identified as priority monitoring areas to gain observed data for all DIN regimes in catchments that flow to the Great Barrier Reef, Australia.

Cuproptosis-related risk score based on machine learning algorithm predicts prognosis and characterizes tumor microenvironment in head and neck squamous carcinomas

Cuproptosis is a recently discovered type of programmed cell death that shows significant potential in the diagnosis and treatment of cancer. It has important significance in the prognosis of HSNC. This study aims to construct a cuproptosis-related prognostic model and risk score through new data analysis methods such as machine learning algorithms for the prognosis analysis of HSNC. Protein-protein interaction network and machine learning methods were employed to identify hub genes that were used to construct a TreeGradientBoosting model for predicting overall survival. The relationship between the risk scores obtained from the model and features such as tumor microenvironment (TME) and tumor immunity was explored. The C-indexes of the TreeGradientBoosting model in the training and validation cohorts were 0.776 and 0.848, respectively. The nomogram based on risk scores and clinical features showed good performance, and distinguished the TME and immunity between high-risk and low-risk groups. The cuproptosis-associated risk score can be used to predict prognoses, TME, and tumor immunity of HNSC patients.

Pattern recognition describing spatio-temporal drivers of catchment classification for water quality

Classification using spatial data is foundational for hydrological modelling, particularly for ungauged areas. However, models developed from classified land use drivers deliver inconsistent water quality results for the same land uses and hinder decision-making guided by those models. This paper explores whether the temporal variation of water quality drivers, such as season and flow, influence inconsistency in the classification, and whether variability is captured in spatial datasets that include original vegetation to represent the variability of biotic responses in areas mapped with the same land use. An Artificial Neural Network Pattern Recognition (ANN-PR) method is used to match catchments by Dissolved Inorganic Nitrogen (DIN) patterns in water quality datasets partitioned into Wet vs Dry Seasons and Increasing vs Retreating flows. Explainable artificial intelligence approaches are then used to classify catchments via spatial feature datasets for each catchment. Catchments matched for sharing patterns in both spatial data and DIN datasets were corroborated and the benefit of partitioning the observed DIN dataset evaluated using Kruskal Wallis method. The highest corroboration rates for spatial data classification with DIN classification were achieved with seasonal partitioning of water quality datasets and significant independence (p < 0.001 to 0.026) from non-partitioned datasets was achieved. This study demonstrated that DIN patterns fall into three categories suited to classification under differing temporal scales with corresponding vegetation types as the indicators. Categories 1 and 3 included dominance of woodlands in their datasets and catchments suited to classify together change depending on temporal scale of the data. Category 2 catchments were dominated by vineforest and classified catchments did not change under different temporal scales. This demonstrates that including original vegetation as a proxy for differences in DIN patterns will help guide future classification where only spatially mapped data is available for ungauged catchments and will better inform data needs for water modelling.

Machine learning-assisted Te-CdS@Mn3O4 nano-enzyme induced self-enhanced molecularly imprinted ratiometric electrochemiluminescence sensor with smartphone for portable and visual monitoring of 2,4-D

Here, a novel and portable machine learning-assisted smartphone-based visual molecularly imprinted ratiometric electrochemiluminescence (MIRECL) sensing platform was constructed for highly selective sensitive detection of 2,4-Dichlorophenoxyacetic acid (2,4-D) for the first time. Te doped CdS-coated Mn₃O₄ (Te-CdS@Mn₃O₄) with catalase-like activity served as cathode-emitter, while luminol as anode luminophore accompanied H₂O₂ as co-reactant, and Te-CdS@Mn₃O₄ decorated molecularly imprinted polymers (MIPs) as recognition unit, respectively. Molecular models were constructed and MIP band and binding energies were calculated to elucidate the luminescence mechanism and select the best functional monomers. The peroxidase activity and the large specific surface area of Mn₃O₄ and the electrochemical effect can significantly improve the ECL intensity and analytical sensitivity of Te-CdS@Mn₃O₄. 2,4-D-MIPs were fabricated by in-situ electrochemical polymerization, and the rebinding of 2,4-D inhibits the binding of H₂O₂ to the anode emitter, and with the increase of the cathode impedance, the ECL response of Te-CdS@Mn₃O₄ decreases significantly. However, the blocked reaction of luminol on the anode surface also reduces the ECL response. Thus, a double-reduced MIRECL sensing system was designed and exhibited remarkable performance in sensitivity and selectivity due to the specific recognition of MIPs and the inherent ratio correction effect. Wider linear range in the range of 1 nM-100 μM with a detection limit of 0.63 nM for 2,4-D detection. Interestingly, a portable and visual smartphone-based MIRECL analysis system was established based on the capture of luminescence images by smartphones, classification and recognition by convolutional neural networks, and color analysis by self-developed software. Therefore, the developed MIRECL sensor is suitable for integration with portable devices for intelligent, convenient, and fast detection of 2,4-D in real samples.

Stream water quality optimized prediction based on human activity intensity and landscape metrics with regional heterogeneity in Taihu Basin, China

The driving effects of landscape metrics on water quality have been acknowledged widely, however, the guiding significance of human activity intensity and landscape metrics based on reference conditions for water environment management remains to be explored. Thus, we used the self-organized map, long- and short-term memory (LSTM) algorithm, and geographic detectors to simulate the response of human activity intensity and landscape metrics to water quality in Taihu Lake Basin, China. Fitting results of LSTM displayed that the accuracy was acceptable, and scenario 2 (regional heterogeneity) was more efficient than scenario 1 (regional consistent) in the improvement of water quality. In the driving analysis for the reference conditions, clusters I and II (urban agglomeration areas) were mainly affected by the amount of production wastewater per unit of developed land and the amount of livelihood wastewater per unit of developed land, respectively. Their optimal values were 0.09 × 10³ t/km² (reduction of 35.71%) and 0.2 × 10³ t/km² (reduction of 4.76%). Cluster III (agricultural production areas) was mainly affected by interference intensity, and the optimal value was 2.17 (increased 38.22%), and cluster IV (ecological forest areas) was mainly affected by the fragmentation of cropland, and the optimal value was 1.14 (reduction of 1.72%). The research provides a reference for the prediction of water quality response and presents an ecological and economic sustainability way for watershed governance.