Air quality is a vital concern globally, and Sri Lanka, according to WHO statistics, faces challenges in achieving optimal air quality levels. To address this, we introduced an innovative IoT-based Air Pollution Monitoring (APM) Box. This solution incorporates readily available Commercial Off-The-Shelf (COTS) sensors, specifically MQ-7 and MQ-131, for measuring concentrations of Carbon Monoxide (CO) and Ozone (O3) ,Arduino and "ThingSpeak" platform. Yet, those COTS sensors are not factory-calibrated. Therefore, we implemented machine learning algorithms, including linear regression and deep neural network models, to enhance the accuracy of CO and O3 concentration measurements from these non-calibrated sensors. Our findings indicate promising correlations when dealing with MQ-7 and MQ-131 measurements after removing outliers.

Diseases caused by bacteria, fungi, and viruses are a problem for many crops. Farmers have challenges when trying to evaluate their crops daily by manual inspection across all forms of agriculture. Also, it is difficult to assess the crops since they are affected by various environmental factors and predators. These challenges can be addressed by employing crop disease detection approaches using artificial intelligence-based machine learning and deep learning techniques. This paper provides a comprehensive survey of various techniques utilized for crop disease prediction based on machine learning and deep learning approaches. This literature review summarises the contributions of a wide range of research works to the field of crop disease prediction, highlighting their commonalities and differences, parameters, and performance indicators. Further, to evaluate, a case study has been presented on how the paradigm shift will lead us to the design of an efficient learning model for crop disease prediction. It also identifies the gaps in knowledge that are supposed to be addressed to forge a path forward in research. From the survey conducted, it is apparent that the deep learning technique shows high efficiency over the machine learning approaches, thereby preventing crop loss.

Air quality is a vital concern globally, and Sri Lanka, according to WHO statistics, faces challenges in achieving optimal air quality levels. To address this, we introduced an innovative IoT-based Air Pollution Monitoring (APM) Box. This solution incorporates readily available Commercial Off-The-Shelf (COTS) sensors, specifically MQ-7 and MQ-131, for measuring concentrations of Carbon Monoxide (CO) and Ozone (O3) ,Arduino and "ThingSpeak" platform. Yet, those COTS sensors are not factory-calibrated. Therefore, we implemented machine learning algorithms, including linear regression and deep neural network models, to enhance the accuracy of CO and O3 concentration measurements from these non-calibrated sensors. Our findings indicate promising correlations when dealing with MQ-7 and MQ-131 measurements after removing outliers.

Assessing the dynamics and patterns of Land Use and Land Cover (LULC) and its transformation is an important practice of urban planners and environmentalists for a variety of applications, including land management, urban climate modeling, and sustainability of any urban region. Monitoring changes in LULC using geospatial techniques can help to identify areas at risk for indefensible land use, low-grade environment, and especially for sustainable urban planning. This study aims to analyze the changing pattern, dynamics, and alteration of LULC using Google Earth Engine (GEE) and Machine Learning Applications for the years 1991, 2001, 2011, and 2022 in the Varanasi City Development Region (VCDR). The LULC classification was divided into seven classes using random forest classification, and Landsat-5(TM) and 9(OLI-2) satellite data were used. Saga GIS has been utilized for the detection of LULC change during the 1991-2022 period. For validation of classification results, accuracy assessment was estimated using error matrices and through user, producer, and overall accuracy estimation. The Kappa statistics were applied for the reliability of the accuracy assessment result. As a result, the built-up area increased by 507.8 percent, and other classes like agricultural, barren, fallow land, and vegetation cover rapidly declined and altered into concrete areas over the period. Water bodies and river sand classes have been slightly converted into different classes. The finding explains that 114.8 km2 of fertile agricultural land, 14.81 km2 barren land, and 12.93 km2 of vegetation cover transformed into impervious surface, which is unsustainable and causes various problems like food scarcity, environmental degradation, and low quality of urban life. This study can be a useful guide for urban planners, academicians, and policymakers by providing a scientific background for sustainable urban planning and management of VCDR and other cities as well.

Assessing the dynamics and patterns of Land Use and Land Cover (LULC) and its transformation is an important practice of urban planners and environmentalists for a variety of applications, including land management, urban climate modeling, and sustainability of any urban region. Monitoring changes in LULC using geospatial techniques can help to identify areas at risk for indefensible land use, low-grade environment, and especially for sustainable urban planning. This study aims to analyze the changing pattern, dynamics, and alteration of LULC using Google Earth Engine (GEE) and Machine Learning Applications for the years 1991, 2001, 2011, and 2022 in the Varanasi City Development Region (VCDR). The LULC classification was divided into seven classes using random forest classification, and Landsat-5(TM) and 9(OLI-2) satellite data were used. Saga GIS has been utilized for the detection of LULC change during the 1991-2022 period. For validation of classification results, accuracy assessment was estimated using error matrices and through user, producer, and overall accuracy estimation. The Kappa statistics were applied for the reliability of the accuracy assessment result. As a result, the built-up area increased by 507.8 percent, and other classes like agricultural, barren, fallow land, and vegetation cover rapidly declined and altered into concrete areas over the period. Water bodies and river sand classes have been slightly converted into different classes. The finding explains that 114.8 km2 of fertile agricultural land, 14.81 km2 barren land, and 12.93 km2 of vegetation cover transformed into impervious surface, which is unsustainable and causes various problems like food scarcity, environmental degradation, and low quality of urban life. This study can be a useful guide for urban planners, academicians, and policymakers by providing a scientific background for sustainable urban planning and management of VCDR and other cities as well.