Sustainable and Green Technologies for Water and Environmental Management

Dynamic texture classification has become an increasingly important research area due to the growing availability of video data and the need for efficient video analysis. Recently, deep learning models have demonstrated remarkable success in automatically classifying dynamic textures. This review provides a comprehensive and concise overview of recent advances in dynamic texture classification, with a particular focus on deep learning-based approaches. We survey the most popular deep learning architectures used for this task, highlighting key findings based on existing deep learning models and offering future research directions. Our review covers network architecture, evaluation criteria, datasets used in video classification, and provides an overview of deep learning methods.

The importance of real-time wastewater quality monitoring in addressing the increasing demand for water and the impact of climate change on wastewater treatment systems is discussed in this work. It highlights the potential of Artificial Intelligence (AI)-based solutions, specifically Artificial Neural Networks (ANNs), to accurately monitor water quality and manage wastewater effectively. Emphasis is placed on the integration of ANNs with the Kalman filter, a technique renowned for enhancing accuracy. This work presents the architecture of a wireless sensor network-based system designed to monitor wastewater quality. Sensor nodes strategically positioned and equipped with microcontrollers, sensors, and transceivers collect data, which undergoes processing using the Kalman filter to estimate and rectify any inaccuracies before transmission to the base station. The system employs multi-sensor data collection and ANN analysis to improve the accuracy and reliability of water quality monitoring. The system's performance is evaluated in terms of recognition and false alarm rates. It achieves a high recognition rate of 95.60% and a low false alarm rate, significantly increasing wastewater utilization efficiency. The ANN decision-making process is efficient, taking only 15 µs. The evaluation also includes the F1 score, demonstrating the system's classification abilities and overall performance. In conclusion, the proposed intelligent system, which integrates ANN and the Kalman filter, represents a notable advancement in wastewater management. It offers superior performance, accurate classification, and rapid response, making it a practical and effective solution for the management of water resources.

Reducing vehicle emissions is crucial for achieving environmental sustainability and mitigating the detrimental impact of air pollution. This scientific article explores the utilization of the YOLOv8 object detection algorithm to detect and mitigate smoke emissions from cars, contributing to the overall reduction of vehicle emissions. By training the YOLOv8 model using a dataset obtained from RoboFlow, consisting of annotated images of smoke-emitting cars, a robust and accurate detection system is developed. The article delves into the process of dataset preparation, including the annotation of images and the creation of corresponding text files with bounding box coordinates around smoke-emitting vehicles. Through iterative model training, which involves optimizing the model's parameters and loss function using backpropagation, the YOLOv8 model becomes adept at detecting and classifying smoke-emitting cars. Once trained, the model can be deployed in real-time scenarios to identify vehicles emitting excessive smoke. Upon detection, measures can be implemented to minimize the smoke percentage in the air. These actions may encompass notifying the driver, suggesting maintenance actions, or even automatically adjusting factors such as vehicle speed and fuel mixture. The integration of fumes and smoke car detection using YOLOv8 into sustainable technologies offers several advantages, including proactive identification of smoke-emitting vehicles and targeted interventions to reduce emissions. This approach fosters responsible vehicle maintenance practices and encourages eco-friendly behaviors among drivers, ultimately contributing to a greener and healthier environment. By embracing these advancements and reducing the smoke percentage in the air, we can take significant strides towards a more sustainable future for all.

The importance of solar energy as a renewable power source has led to increased adoption of solar modules for electricity generation. However, faults in solar cells can significantly impact their performance and efficiency. Manual defect detection is time-consuming and subjective, hence the need for an intelligent and efficient detection solution. In this study, we propose a method for detecting defective solar cells in electroluminescence imaging using an advanced object detection algorithm, specifically YOLO5 version. An important step in the algorithm is to formulate the detection problem in terms of real-time detection of defects. We evaluate our method on a dataset of different types of solar modules containing a total of 240 solar cells with various defects, including finger interruptions, microcracks, electrically separated or degraded cell parts and material defects. Experimental evaluation on solar cell images extracted from high-resolution electroluminescence images of photovoltaic modules datasets reveals that the proposed framework successfully mitigates the influence of defect image degradation. The precision and recall confidence curves indicate a moderate performance, suggesting that the framework shows promising capabilities in detecting and localizing defects. This research contributes to the widespread adoption and sustainable utilization of solar energy, ensuring the optimal performance and longevity of solar cells.

Accurate multi-temporal satellite image matching plays a crucial role in monitoring agricultural areas, particularly in the context of water resource management. This study presents a feature-based approach for multi-temporal satellite image matching, using the VGG16 model. More specifically, our research focuses on the application of this approach to satellite images of agricultural dams in order to assess the reduction in water quantity caused by drought. Using the discriminant features extracted by the VGG16 model, we establish points of correspondence between images captured at different times, enabling precise alignment. Experimental results demonstrate the effectiveness of our approach in achieving accurate alignment of agricultural dam images, this study contributes to the advancement of feature-based matching techniques and their application in satellite image analysis for agricultural monitoring.

This research intends to unveil the positive implications of using blockchain-based technology in international trade, specifically in importation customs clearance activities. The application of blockchain technology in customs clearance offers several benefits, such as simplifying customs procedures, improving global supply chain management, preventing customs-related risks, and enabling real-time product verification in terms of quantity, quality, and origin. Through qualitative analysis using Nvivo software, this research examines the implementation of the blockchain platform PortNet in Morocco and its impact on import customs procedures. The findings suggest that the use of blockchain technology through PortNet has effectively facilitated and streamlined the import customs process. By utilizing blockchain technology, this study highlights the potential for increased efficiency, transparency, and reliability in international commercial transactions, which can contribute to improved trade facilitation and economic growth.

Effective and sustainable water resource management necessitates precise and specific understanding of these resources. Surface flows arise from intricate interactions among subsurface hydrogeological processes, spatial and temporal fluctuations in meteorological inputs, and the unique characteristics of river systems in basins. However, current water resource management heavily relies on data from hydrometric and rainfall stations, which frequently exhibit gaps and inaccuracies. Furthermore, most of these stations are positioned at the outlets of basins, thereby monitoring extensive areas. It's crucial to note that basins might not always be the optimal choice for an in-depth water resource analysis, as sub-basins can exhibit significant geological, lithological, and topographical differences. Consequently, the cumulative flow rates recorded at these stations amalgamate contributions from various aquifers, each responding differently, particularly during periods of low flow. These distinctions become complex to redistribute spatially once consolidated. This study introduces a methodology aimed at generating hydrological data on a more refined scale, shifting the focus from the entire basin to more standardized units termed as unitary basins. This approach has been implemented in the Srou basin, a key tributary of the Oum Er Rbia river. The basin was divided into smaller catchments, with flow measurements conducted between 2016 and 2019, excluding periods of direct rainfall. These assessments underscore the diverse flow characteristics within the Srou river system, highlighting the necessity of considering these variations for effective water resource management.

Soil erosion is one of a major environmental issue in many regions of the world, especially in the Mediterranean areas. Due to their climate aggressivity and soil fragility, majority of Mediterranean countries are affected by water erosion. With its localization in the Middle Atlas of Morocco, the upstream part of Oum Err Bia basin is one of the influenced areas by soil erosion. This part of Morocco characterized by steep slopes and weak rocks which make soils vulnerable to water erosion. The purpose of this study is to quantify soil erodibility by applying Revised Universal Soil Loss Equation (RUSLE(, and validate it in the four selected catchments (Tamadout, Faraoun, Almou and Ait Addi catchments). Besides, 32 bottles of samples were collected in the outlet of representative catchments so as to estimate the concentration of sediment. As a result, the obtained annual soil loss average was 145 75 t ha⁻¹ yr⁻¹. However, the concentration of sediment ranged from 0.2 to 234.5 g/l⁻¹. The results confirmed that different factors affect and control the soil loss like intense rainfall events, land uses type, lithology and human activities.

In this paper, we address the aforementioned limitations of conventional scanners in cardiac imaging and propose a solution to optimize their functionality. Specifically, we explore the integration of Backstepping control as a means to overcome these challenges. By incorporating Backstepping control algorithms into the imaging process of a conventional scanner, we aim to enhance image quality and accuracy in capturing cardiac images. Backstepping control is a control theory approach known for its ability to compensate for the motion of dynamic systems. By precisely tracking the movement of the heart during image acquisition, we can mitigate motion artifacts and improve the clarity of cardiac images. Through experimental investigations and simulations, we evaluate the effectiveness of the Backstepping control integration in a conventional scanner for cardiac imaging. We compare the results with traditional imaging techniques and specialized cardiac scanners, such as Cardiac CT or Coronary CT, to demonstrate the potential of our approach.

This paper presents a novel method for blind source extraction of the fetal electrocardiogram (ECG) using the short-time Fourier transform. Unlike previous studies that primarily focused on time–frequency methods for speech signals, this research addresses the more challenging task of analyzing non-stationary biomedical signals, such as the fetal and maternal electrocardiograms. One significant advantage of these biomedical signals is their remarkable energy distribution variation over time and frequencies, which is evident in their spectrograms. The proposed approach aims to accurately separate these mixed signals without prior knowledge of their sources. Through comprehensive simulations and rigorous experimental evaluations, the results demonstrate the high performance and effectiveness of the method in successfully extracting fetal and maternal ECG signals. This advancement has promising implications for enhancing fetal monitoring and maternal health assessment during pregnancy.

Flow duration curve combines in one curve the flow characteristics of a stream throughout the range of discharge. It can also facilitate the assessment of both the severity and seasonal fluctuations of low-flow periods. This curve offers a valuable tool for comprehensively understanding the dynamics of water scarcity over time. The purpose of this study is to evaluate the intensity and seasonal patterns of low flow in the Tassaout River basin, upstream of the Moulay Youssef dam. This basin experiences a semi-arid climate characterized by limited rainfall. Furthermore, alongside the constrained distribution of water resources, the region faces growing demands due to ongoing climate change. Low-flow events are recurrent on a seasonal basis, and their severity can be influenced by annual variations in rainfall. This article aims to contribute to the examination of low-flow period severity and seasonality through the analysis of recorded water deficits during these periods. For this purpose, the Sequent Peak Algorithm (SPA) method was employed to extract water deficit volumes. The low-flow threshold was determined using the Q75 indicator derived from the flow duration curve, which was constructed from daily discharge data collected at the Ait Tamlil and Tamsemat gauging stations, spanning the period from 1978 to 2016.

The effective monitoring of nitrogen dioxide (NO\(_{{2}}\)) assumes pivotal significance in fostering sustainable environments, primarily due to its substantial impact on air quality. This study constitutes a significant stride in this direction by harnessing the capabilities of Differential Optical Absorption Spectroscopy (DOAS) to measure and comprehend NO\(_{{2}}\) levels, thereby shedding comprehensive light on its vertical distribution within the troposphere. The DOAS method also offered a unique advantage in terms of identifying and quantifying trace gases with unknown vertical columns in the designated region. These intricate tasks are accomplished by leveraging UV and visible wavelength range spectroscopy, which makes use of scattered sunlight as the fundamental light source. Our work delves into the technical intricacies underpinning DOAS while emphasizing the broader context of its utility. These include the use of pixel-based gas profile analysis, statistical methods, and Python scripts to analyze the measured gas concentration data. By capitalizing on these advanced techniques, a comprehensive understanding of trace gas distribution and behavior is achieved, thereby making a substantial contribution to the enhancement of environmental monitoring strategies. In essence, our work offers both technical and analytical insights that support sustainable practices for monitoring and managing air quality.

The endophytic fungus Trichoderma asperellum known as biological control agent has also capacity to stimulate plant growth. Tomato plants were treated with the moroccan T. asperellum laboratory-made biofungicidal and biostimulant product slurry at a concentration of 107 conidia.mL⁻¹ by dipping before planting and by fertigation with different volumes, 5 L, 10 L, 15 L and 20 L, three times every 20 days during cultivation. The tomato plants grew well compared to the control plants. The aerial part length, numbers of leaves, flowers and fruits respectively increased with time varying from 48.29 to 55.64/34.28 cm; 10.36 to 12.56/8.6; 6.86 to 9.72/5.2; 0 to 0.26/0 after the first application, from 79. 06 to 91.09/ 51.83 cm; 27.6 to 32.43/22.53; 23.9 to 42.4/9.8; 3.84–5.88/2.74 after the second application and from 95.55 to 112.12/70.53 cm; 39.92 to 45.62/22.48; 17.08 to 58.99/7.94; 14.32 to 23.2/12.14 after the third application. By the end of the trial, the root part length and the fresh weights of the aerial and root parts attained 53/48 cm; 555.96/238.3 g and 31.76/20.06 g respectively. T. asperellum was able to colonize the roots, stems and leaves of the tomato plants, with significant re-isolation percentages reaching 90%, 85% and 66.66%. The T. asperellum based bioproduct has shown its ability to promote the growth of tomato plants, the gain percentages of the different agronomic parameters are very important which can be multiplied by 2, 3 or even 5, as in some cases.

The different Trichoderma asperellum—Pyraclostrobin + Boscalid preventive treatment programs were applied before inoculation with Colletotrichum gloeosporioides, to the aerial parts of Camarosa strawberry plants. They reduced anthracnose symptoms for 80 days, The disease severity reduction percentages on leaves were ranged from 66.66 to 99.1%. The numbers of symptomatic flowers, green and red strawberries are zero to low compared to the inoculated control, the reduction percentages varied between 94.1–100%, 92.25–100% and 81.35–100%. The C. gloeosporioides inoculum on leaves and petioles of treated plants was low to nil compared to plants inoculated with the pathogen, the re-isolation percentages fluctuated from 0 to 25%/100% and 0 to 33%/100%. The combined treatments provided better development of the aerial and root parts than the inoculated plants. The aerial perpendicular diameter growth, root length development and their fresh weights reached respectively 16.66/7.66 cm, 35.33/14 cm, 8.6/3.3 g and 21.83/9.16 g. The Trichoderma asperellum—Pyraclostrobin + Boscalid combination provided integrated protection of strawberry plants against anthracnose and compatibility between biological control agent and fungicide.

Smart devices are interconnected devices that collect and exchange data wirelessly through sensors, routers, etc. Industries use IoT to optimize their functioning to reduce environmental impacts and make a more sustainable approach. Some of the objectives would be: increasing resource efficiency by monitoring patterns and optimizing the usage, monitoring the Environment is beneficial for the air, water, and soil quality, and decisions can be taken based on the real-time data that the smart objects generate. In this study topic, we will discuss how IoT technology is going to help the environment through smart objects (i.e. sensors, routers) in maintaining the resources that are not renewable, water resource management, Green transportation like electric buses, intelligent traffic management, and many more topic’s through which IoT technology can reduce the dependency of the resources in real-time. The overall output of the IoT technology with the use of smart objects/devices concerning the area of application would be enhancing resource efficiency, lower gas emissions, enhancing waste management such as recycling, cost savings, real-time data present while decision-making, and Sustainable infrastructure such as smart building. Some of the real-time examples are Alexa, Connected cars, and Fitness watches.

This study focuses on sustainable water management practices at the city corporation level in Bangladesh, specifically comparing the cities of Sylhet and Barisal. The study aims to examine the current state of water management, identify gaps in sustainable practices, explore challenges and opportunities associated with integrating sustainable water sources, evaluate the role of city corporations in water governance, and assess the impact of community participation on sustainable water management. Primary data were collected through surveys, analyzing water sources, ownership patterns, water safety, availability, and management practices. The findings highlight variations in water sources, ownership, safety, availability, and satisfaction between the two cities. The research concludes that effective strategies are required to address the specific challenges in each city, including improving water source ownership, enhancing water safety and quality, ensuring sufficient water availability, and promoting sustainable water management practices. By implementing effective solutions and strengthening governance frameworks, both cities can achieve sustainable water management and provide clean and safe water to their residents.

Green energy is a key factor in replacing fossil fuels, which have harmful effects on the environment. And in reducing air pollution, benefits not just the planet, but human and animal health too. The growing reliance on the Internet of Things (IoT) has contributed to the evolution of the energy sector. Today, green energies benefit through the Internet of Things (IoT), which allows industries to optimize the use of data and enhance efficiency and sustainability. To enhance all technical and economic aspects of the green and sustainable energy production process. Integrating microalgae into the Internet of Things is leading to the creation of new innovative technologies. Today, developing and adopting digitization technologies in the algae sector has become paramount to achieving the desired production levels. This chapter discusses the use of advanced process control strategies, improved digitization, and data analysis in microalgae cultivation processes.

In Morocco, the sour orange (Citrus aurantium L.) is the most anciently used rootstock, it remains dominant. Due to its better affinity with most commercial varieties, its adaptation to a wide range of soils and mainly due to its resistance to root rot caused by Phytophthora spp. However, it gives susceptible associations to tristeza. In vivo, several methods were used for the screening of citrus rootstocks in relation to Phytophthora spp. The objective of our experimentation is the development of an in vitro screening test of rootstocks caused by Phytophthora parasitica. Plants of Citrumelo (57. 98. 502), Poncirus Trifoliata, Citron troyer, Citron Troyer c 35 B 6 A11, Cleopatra mandarin tree x CC 30 575, Cleopatra mandarin tree xP.T 30 584, Cleopatra mandarin tree x cc B2 30 576, Mandarin tree changsa B2, Mandariniecleop X CC 30,577 and a South African Hybrid aged 2 months were watered daily and fertilized every 15 days using a nutrient solution. Inoculation was done by soaking the root systems in a spore suspension of P. parasitica for 24 h. Inoculation with P. parasitica caused root rot (Rot-tips) with a reduction in feeder fiber production and colonization of root systems that varied between rootstocks. Indeed, the Mandarin hybrids Cleopatra x cc 30 575 and the Mandariner Cleopatra x cc B2 30 576, were the most susceptible rootstocks to P. parasitica while the hybrids Citrange Troyes, Citrange Troyer C 35 B 6 A11 and the hybrid of South Africa are the most resistant rootstocks. Variability of rootstocks colonization by P. parasitica is thought to be variability in the production ability of 6, 7-dimethoxycoumarin (DMC) in root tissues of rootstocks.

Microorganisms are to blame for contaminating water resources, toxic substances or industrial waste. It can be found in rivers, aquifers and brackish bodies of water, as well as in rain water, dew, salt water, snow and arctic pack oceans. Bio sensing techniques based on cell growth use the full range of existing cytotoxic response to external inputs, via a to indicate the toxicity of aquatic targets. These bio-detection techniques can provide an effective means of indicating the water’s toxicity to the safety of humans and the environment and health of marine organisms. The substantial increase in the level of pollutants entering fresh water requires rapid and accurate methods to monitoring the aqueous environment and detection of water aquatic aquatic poisoning. In this project, we review the recent evolution of current water biosensing techniques based on cell culture quality assessment, explain their major properties and capabilities, and the prospects for development in the coming years.