Forest Fire Hazard Assessment using Remote Sensing Data and Machine Learning, Case Study of Jijel, Algeria by Matougui Zakaria, Zouidi Mohamed

“…Evaluation metrics such as Receiver Operating Characteristic Area Under the Curve, F1 score and accuracy, supported by repeated cross-validation, were used to gauge performance. Both models performed well (with an average area under the curve of 0.977 and 0.984, respectively), with HGB maintaining a marginal but consistent advantage over KNN, with relatively low standard deviations, suggesting stability in its predictive capability. …”
Get full text

Urban tree species benchmark dataset for time series classificationEasyData - Data Terra by Clément Bressant, Romain Wenger, David Michéa, Anne Puissant

“…Model outputs—predicted species, confidence scores, and correctness flags—are provided, along with an interactive t-SNE visualization of the latent feature space for interpretability and error analysis. …”
Get full text

Transcending the urban–rural dichotomy: inequality in urban green space availability among urban neighbourhoods, urban villages and rural villages in Guangzhou, China by Fubin Luo, Yunzheng Zhang, Luyang Zhang

“…This study unveils the spatial disparity of UGS inequality among different types of neighbourhoods, providing insights into equal green space planning and contributing to environmental justice.…”
Get full text

Discriminative Cross-Modal Attention Approach for RGB-D Semantic Segmentation by emad mousavian, Danial Qashqai, Shahriar B. Shokouhi

“…By integrating the DCMAF module with efficient channel- and spatial-wise attention modules, we introduce the Discriminative Cross-modal Network (DCMNet), a scale- and appearance-invariant model. …”
Get full text

Cosmological Constraints from Combining Photometric Galaxy Surveys and Gravitational Wave Observatories by E.L. Gagnon, D. Anbajagane, J. Prat, C. Chang, J. Frieman

“…More interestingly, the optical-GW data combination provides tight constraints on models with primordial non-Gaussianity (PNG), due to the predicted scale-dependent bias in PNG models on large scales. …”
Get full text

DHS-YOLO: Enhanced Detection of Slender Wheat Seedlings Under Dynamic Illumination Conditions by Xuhua Dong, Jingbang Pan

“…Compared to the existing models, the proposed model achieved the best performance with precision, recall, mAP50, and mAP50-95 values of 94.1%, 91.0%, 95.2%, and 81.9%, respectively. …”
Get full text

Computational principles of neural adaptation for binaural signal integration. by Timo Oess, Marc O Ernst, Heiko Neumann

“…The circuit incorporates an adaptation mechanism operating at the synaptic level based on local inhibitory feedback signals. The model's predictive power is demonstrated in various simulations replicating physiological data. …”
Get full text

Estimating canopy height in tropical forests: Integrating airborne LiDAR and multi-spectral optical data with machine learning by Brianna J. Pickstone, Hugh A. Graham, Andrew M. Cunliffe

“…Overall, this study reveals that the inclusion of PlanetScope and the application of more complex CNN models is not necessary for canopy height predictions in tropical forests, as open-access optical data combined with simpler tree-based models, such as RF, demonstrate comparable performance.…”
Get full text

Carbonate Seismic Facies Analysis in Reservoir Characterization: A Machine Learning Approach with Integration of Reservoir Mineralogy and Porosity by Papa Owusu, Abdelmoneam Raef, Essam Sharaf

“…This comparative ML, which was leveraged with seismic resolution data preconditioning, predicted geologically plausible seismic facies, i.e., seismic facies with spatial continuity, consistent morphology across seismic bands, and two ML algorithms. …”
Get full text

Global and regional patterns of soil metal(loid) mobility and associated risks by Chongchong Qi, Tao Hu, Yi Zheng, Mengting Wu, Fiona H. M. Tang, Min Liu, Bintian Zhang, Sybil Derrible, Qiusong Chen, Gongren Hu, Liyuan Chai, Zhang Lin

“…Here we show a theory-guided machine learning model that predicts soil metal(loid) fractionation across the globe. …”
Get full text

The hydrological impact of greening and climate change on the Mu Us Sandy land of China under the background of declining ecological efficiency by Jiazheng Li, Rong Wu, Mengjing Li, Zijun Wang, Chenfeng Cui, Junrong Liu

Get full text

Selecting the best habitat mapping technique: a comparative assessment for fisheries management in Exmouth Gulf by Scott N. Evans, Scott N. Evans, Nick Konzewitsch, Renae K. Hovey, Gary A. Kendrick, Lynda M. Bellchambers

“…While advances in remote sensing, acoustic methodologies, geostatistical modelling, and predictive species distribution models have improved our ability to map underwater habitats, selecting the most appropriate approach, particularly in turbid or remote regions, remains challenging. …”
Get full text

Ecological network construction and land degradation risk identification in the Yellow River source area by Haoxiang Zhang, Qian Song, Shiru Wang, Jianyun Zhao, Wenming Gao

“…Based on ordered weighted average operator, morphological spatial pattern analysis, ecological sensitivity, circuit theory, CA-Markov model, kernel density analysis, and other methods, this study aims to consider the positive and negative connections of the network thus constructing the ecological and risk network and predicting the potential risk areas in the future. …”
Get full text

Identifying Priority Areas for the Indian Leopard (Panthera pardus fusca) Within a Shared Landscape by Aparna Kolekar, Kimberley Hockings, Kristian Metcalfe, Sanjay Gubbi

“…Environment variables were chosen to reflect land use, climatic, topographic, and human disturbances that could affect habitat selection at a resolution of 0.1 km2. The mean ensemble model was projected to the state of Karnataka. Habitat selection predicted by the ensemble model was driven by proximity to forest cover and rocky outcrops, higher precipitation, and negatively by distance to cropland and roads. …”
Get full text

Enhancing Road Scene Segmentation With an Optimized DeepLabV3+ by Zhe Ren, Libao Wang, Tianming Song, Yihang Li, Jian Zhang, Fengfeng Zhao

“…Semantic segmentation, as a dense predictive task, is inevitably affected by various external factor, making common road image semantic segmentation models unable to meet dual demands of high accuracy and real-time performance in unstructured road scenarios. …”
Get full text

Analysis and Optimization of Soil Nail Parameters in a Deep Foundation Pit of Silty Clay Based on Response Surface Methodology by FAN Cheng, WANG Zi-yuan, QI Peng-fei, ZHANG Hong-bin, ZHANG Tiao-tiao

“…In the combined effect of support parameters, the soil nail length and spacing have the greatest impact on the safety factor. The predictive model established by the response surface method can provide the best optimization scheme. …”
Get full text

Numerical investigation of nonlinear interaction between salinity- and sediment-induced stratification in highly turbid estuaries and coastal seas by Jian Zhou, Bing Sun, Huiming Zhang, Saiyu Yuan, Hongwu Tang

“…These findings highlight the necessity of incorporating sediment's modulation of classical strain-induced periodic stratification due to salinity gradients in numerical models to improve predictions of buoyancy and stability in highly turbid estuarine and coastal systems.…”
Get full text

Artificial intelligence and machine learning to enhance critical mineral deposit discovery by Rhys S. Davies, McLean Trott, Jaakko Georgi, Alexander Farrar

“…Broader adoption of statistical methods, integrated spatial models, and innovative data preparation techniques can address the inconsistencies in exploration datasets. …”
Get full text

Stable developmental patterns of gene expression without morphogen gradients. by Maciej Majka, Nils B Becker, Pieter Rein Ten Wolde, Marcin Zagorski, Thomas R Sokolowski

“…The optimal parameter regime found in simulations of the embryo model closely agrees with the predictions of our coarse-grained stability theory. …”
Get full text

Low-Shot Weakly Supervised Object Detection for Remote Sensing Images via Part Domination-Based Active Learning and Enhanced Fine-Tuning by Peng Liu, Boxue Huang, Tingting Jin, Hui Long

“…ACRT contributes to refining the model at different active stages, especially for under-performed classes, and to reducing the impact of noisy predictions. …”
Get full text