Author: Latest Results

Assessing the impact of climate change by using Mann–Kendall, Pettitt and statistical downscaling model (case study: Tabriz station)

Latest Results

Abstract

Climate change is one of the most important phenomena in large cities. This phenomenon causes various disasters such as floods, drought, water insecurity, water war and summer heat waves in cities. In this research, different methods, including the statistical downscaling method, Mann–Kendall, Pettitt, a precipitation index (PI), a temperature index, a weighted precipitation index (WPI), a weighted temperature index (WTI) and frequency analysis, have been used for assessment of precipitation and temperature time series in Tabriz city, located in the northwest of Iran. Here, data from the base time period (i.e., 1951–2022) and future time period (2022–2100) were considered to analyze. Three distinct scenarios were used in the study, namely RCP 2.6, RCP 4.5 and RCP 8.5. Results indicated that in the base period, the monthly and annual precipitation time series showed insignificant statistical trends. In the base period, the mean of the annual precipitation time series decreased suddenly such that its mean value declined from 316.32 mm (in the first sub period, i.e., 1951–1982) to 261.51 mm (in the subsequent sub period, i.e., 1982–2022). Also, the average temperature time series on monthly and annual scales showed statistically significant upward trends. A significant change in the average annual temperature was detected in 1994, in which its mean value jumped from 11.76 to 13.32 °C. Future annual precipitation (2022–2100) time series showed a statistically significant upward trend using RCP 2.6. However, using the RCP 4.5 and RCP 8.5 scenarios, trends in this parameter will not be significant in the future period. In addition, in the future period, the average annual air temperature in Tabriz has been shown to be increased from 12.35 to 12.75 °C using the three used RCPs. The values of three indices, namely TI, WTI, PI and WPI, indicated that in the future, the number of dry and warm periods will be more than the wet and cold periods. Also, the frequency analysis showed that the intensity, duration and precipitation pattern in the future period will be somewhat different from that of the base period. In Tabriz, the average annual temperature in most of the future years will be between 12 and 13 °C. Therefore, it can be concluded that climate change has affected Tabriz's climate since the end of the nineteenth century and is anticipated to continue in the following years.

Optimizing U-Net CNN performance: a comparative study of noise filtering techniques for enhanced thermal image analysis

Latest Results

Abstract

Infrared thermal imaging presents a promising avenue for detecting physiological phenomena such as hot flushes in animals, presenting a non-invasive and efficient approach for monitoring health and behavior. However, thermal images often suffer from various types of noise, which can impede the accuracy of analysis. In this study, the efficacy of different noise filtering algorithms is investigated utilizing filtering algorithms as preprocessing steps to enhance U-Net convolutional neural network (CNN) performance in processing animal skin infrared image sets for hot flush recognition. This study compares the performance of four commonly used filtering methods: mean, median, Gaussian, and bilateral filters. The impact of each filtering technique on noise reduction and preservation of features critical for hot flush detection is evaluated in a machine learning hot flush detection algorithm. The optimal filtering for skin thermal imaging was a median filter which significantly improved the U-Net CNN’s ability to accurately identify hot flush patterns, achieving an Intersection over Union score of 92.6% compared to 90.4% without filters. This research contributes to the advancement of thermal image processing methodologies for animal health monitoring applications, providing valuable insights for researchers and practitioners in the field of veterinary medicine and animal behavior studies utilizing autonomous thermal image segmentation.

A network intrusion detection system based on deep learning in the IoT

Latest Results

Abstract

As industrial and everyday devices become increasingly interconnected, the data volume within the Internet of Things (IoT) has experienced a substantial surge. This surge in data presents a heightened risk of IoT environments being vulnerable to cyber attacks, which poses a significant threat to the seamless functioning of both industrial and daily activities. Therefore, the implementation of Network Intrusion Detection System (IDS) is vital for safeguarding the security of IoT network environments. This paper introduces a network intrusion detection model based on deep learning (DL). The model aims to enhance detection accuracy by extracting features from both the spatial and temporal dimensions of network traffic data. To tackle the challenge of low detection accuracy arising from data imbalance, in this study, a Conditional Tabular Generative Adversarial Network (CTGAN) is utilized to generate synthetic data for the minority class. The objective is to enhance the volume of minority class samples, address data imbalance, and subsequently enhance the accuracy of network intrusion detection. The classification performance of the proposed model is validated on UNSW-NB15, CIC-IDS2018, and CIC-IOT2023 datasets. The experimental findings demonstrate that the suggested model attains elevated levels of classification accuracy across all three datasets. The model presented in this article is particularly well suited to handle multi-class intrusion detection tasks. The model demonstrates superior performance compared to other models used for comparison.

Depiction of Drought Over Africa in the Light of Changing Climate from CMIP6 Models

Latest Results

Abstract

Drought stands as a prevalent weather-related natural climatic disaster on a global scale. This study employs twenty GCMs from CMIP6 to investigate hydrological drought characteristics (frequency, duration, and intensity) across Africa under four SSPs (shared socioeconomic pathway) scenarios: SSP1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5 spanning three designated periods: 2021–2040 (near-term), 2041–2060 (mid-term), and 2081–2100 (long-term). The (SPEI) at a 12-month scale and employs bias correction on the multi-model ensemble mean extracted from GCMs of the CMIP6 project via cumulative distribution function (CDF). Mann–Kendall approach was implemented for trend and the SPEI-12-based drought trend from 1979 to 2014 displays a negative trajectory of − 0.05/a for Africa, with similar figures for specific regions: Northern Africa (NAF) at − 0.06/a, Sahara (SAH) at − 0.05/a, Western Africa (WAF) at − 0.01/a, Central Africa (CAF) at − 0.02/a, Eastern Africa (EAF) at − 0.06/a, and Southern Africa (SAF) at − 0.03/a. Notably, the severe drought characteristics are manifested as a 6-month duration, 12 occurrences, and an intensity of − 1.9 events over Africa. The highest duration and frequency are observed over NAF at 7.5-month and 15.1 occurrences, respectively, while the most extreme intensity of − 2.3 events is noted over SAH. In addition, future droughts are expected to be lower frequency, extended duration, and more intense. Extreme scenarios indicate values of − 2.1, − 2.2, and − 2.6 events for Africa in the periods 2021–2040, 2041–2060, and 2081–2100, respectively, compared to − 1.99 in the historical period. The intensity of the drought is expected to increase across all sub-regions, with SAH and NAF projecting the worst conditions with − 2.4, − 2.8, and − 3.0 events respectively for SAH and − 2.2, − 2.7, and − 3.0 events for NAF. Africa’s droughts are predicted to last 6, 8, and 13 months, significantly longer than the usual 4-month period. As the historical events of 17 times is anticipated to drop to 6, 5, and 3 times, respectively. The insights derived from this study could provide a foundational basis for devising effective drought adaptation strategies in Africa. Given the anticipated severity of drought events, prioritizing plans to cope with such challenges is of paramount importance.

Novel dual-image encryption scheme based on memristive cellular neural network and K-means alogrithm

Latest Results

Abstract

In this paper, we propose a lossless encryption method based on dual images. A cosine perturbation is added to the generalized voltage-controlled memristor, thus constituting a generalized voltage-controlled cosine memristor. And the characteristics of the memristor are analyzed and introduced into a four-dimensional cellular neural network, thus constituting the memristor-based four-dimensional cellular neural network (M4DCNN). The parameters of the M4DCNN are adjusted to achieve a hyperchaotic state for the diffusion and scrambling stages of the image. On the key, the partial key is obtained by K-means algorithm to make the key more random. In the scrambling phase, perturbed logistic chaotic map is introduced in this paper, which makes the image pixels better satisfy the avalanche effect. Through security analysis and comparison with other encryption methods, it is found that the encryption method shows to have good encryption effect in various indexes such as key sensitivity, key space, pixel correlation, information entropy, resistance to shear attack, resistance to noise attack, UACI and NPCR analysis.

Enhancing spatial resolution of satellite soil moisture data through stacking ensemble learning techniques

Latest Results

Abstract

Soil moisture (SM) is a critical variable influencing various environmental processes, but traditional microwave sensors often lack the spatial resolution needed for local-scale studies. This study develops a novel stacking ensemble learning framework to enhance the spatial resolution of satellite-derived SM data to 1 km in the Urmia basin, a region facing significant water scarcity. We integrated in-situ SM measurements (obtained using time-domain reflectometry [TDR]), Soil Moisture Active Passive (SMAP) and Advanced Microwave Scanning Radiometer 2 (AMSR2) SM products, Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature and vegetation indices, precipitation records, and topography data. Ten base machine-learning models were evaluated using the Complex Proportional Assessment (COPRAS) method, and the top-performing models were selected as base learners for the stacking ensemble. The ensemble model, incorporating Random Forest, Gradient Boosting, and XGBoost, significantly improved SM estimation accuracy and resolution compared to individual models. The XGBoost and Gradient Boosting meta-models achieved the highest accuracy, with an unbiased root mean square error (ubRMSE) of 1.23% m3/m3 and a coefficient of determination (R2) of 0.97 during testing, demonstrating the exceptional predictive capabilities of our approach. SHapley Additive exPlanations (SHAP) analysis revealed the influence of each base model on the ensemble’s predictions, highlighting the synergistic benefits of combining diverse models. This study establishes new benchmarks for soil moisture monitoring by showcasing the potential of ensemble learning to improve the spatial resolution and accuracy of satellite-derived SM data, providing crucial insights for environmental science and agricultural planning, particularly in water-stressed regions.

Saltwater intrusion simulations in coastal karstic aquifers related to climate change scenarios

Latest Results

Abstract

Coastal zones are crucial ecosystems supporting significant biodiversity and pertinent socio-economic activities. However, anthropogenic development contributes to socio-environmental complexities, particularly public water supply threats caused by climate change. This research presents a case study on the north-western coast of Yucatan, Mexico, which models potential saltwater intrusion in groundwater for multiple projections of sea level rise and recharge change due to climate change and its implications for the public water supply of the regional population and ecosystem. For this purpose, a previously calibrated and validated numerical model is employed, adapting its boundary conditions, keeping its calibrated hydrogeologic parameters, and considering the 2040 and 2100 climate change projections. Simulation results show that under these projections, significant saltwater intrusion may occur, reducing freshwater thickness due to increased salinity in groundwater and a loss of freshwater sources resulting from brackish-saline wedge intrusion. These scenarios are of particular concern as freshwater in this coastal region is the main source for public water supply and for freshwater input in coastal ecosystems. Moreover, this study underscores the susceptibility of karstic aquifers to salinization, especially in the face of rising sea levels, given their unique hydrogeological characteristics and substantial responsiveness to marine forcings. In spite of the uncertainties in global climate change predictions, this study enhances our understanding of the dynamics of these unique aquifers, and presents future saltwater intrusion projections that offer valuable technical insights to design and implement pertinent and resilient coastal aquifer management strategies.

HiCPC: A new 10-km CMIP6 downscaled daily climate projections over China

Latest Results

Abstract

Accurate climate projections are critical for various applications and impact assessments in environmental science and management. This study presents HiCPC (High-resolution CMIP6 downscaled daily Climate Projections over China), a novel dataset tailored to China’s specific needs. HiCPC leverages outputs from 22 global climate models (GCMs) from the Coupled Model Intercomparison Project Phase 6 (CMIP6). To address inherent biases in daily GCM simulations, an advanced Bias Correction and Spatial Disaggregation (BCSD) method is employed, using the China Meteorological Forcing Dataset (CMFD) as a reference. HiCPC offers detailed daily precipitation and temperature data across China at an enhanced spatial resolution of 0.1° × 0.1°. It covers both the historical period (1979–2014) and future projections (2015–2100) based on four CMIP6 Shared Socioeconomic Pathways (SSPs) scenarios (SSP1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5). Upon validation, HiCPC demonstrates good performance, surpassing CMIP6 GCMs across the historical period. This reinforces its significance for essential research in climate change evaluation and its associated implications within China.

Artificial intelligence reveals past climate extremes by reconstructing historical records

Latest Results

Abstract

The understanding of recent climate extremes and the characterization of climate risk require examining these extremes within a historical context. However, the existing datasets of observed extremes generally exhibit spatial gaps and inaccuracies due to inadequate spatial extrapolation. This problem arises from traditional statistical methods used to account for the lack of measurements, particularly prevalent before the mid-20th century. In this work, we use artificial intelligence to reconstruct observations of European climate extremes (warm and cold days and nights) by leveraging Earth system model data from CMIP6 through transfer learning. Our method surpasses conventional statistical techniques and diffusion models, showcasing its ability to reconstruct past extreme events and reveal spatial trends across an extensive time span (1901-2018) that is not covered by most reanalysis datasets. Providing our dataset to the climate community will improve the characterization of climate extremes, resulting in better risk management and policies.