Internet of Things (IoT)-based automation of agricultural events can change the agriculture sector from being static and manual to dynamic and smart, leading to enhanced production with reduced human efforts. Precision Agriculture (PA) along with Wireless Sensor Network (WSN) are the main drivers of automation in the agriculture domain. PA uses specific sensors and software to ensure that the crops receive exactly what they need to optimize productivity and sustainability. PA includes retrieving real data about the conditions of soil, crops and weather from the sensors deployed in the fields. High-resolution images of crops are obtained from satellite or air-borne platforms (manned or unmanned), which are further processed to extract information used to provide future decisions. In this paper, a review of near and remote sensor networks in the agriculture domain is presented along with several considerations and challenges. This survey includes wireless communication technologies, sensors, and wireless nodes used to assess the environmental behaviour, the platforms used to obtain spectral images of crops, the common vegetation indices used to analyse spectral images and applications of WSN in agriculture. As a proof of concept, we present a case study showing how WSN-based PA system can be implemented. We propose an IoT-based smart solution for crop health monitoring, which is comprised of two modules. The first module is a wireless sensor network-based system to monitor real-time crop health status. The second module uses a low altitude remote sensing platform to obtain multi-spectral imagery, which is further processed to classify healthy and unhealthy crops. We also highlight the results obtained using a case study and list the challenges and future directions based on our work.

Indoor air quality typically encompasses the ambient conditions inside buildings and public facilities that may affect both the mental and respiratory health of an individual. Until the COVID-19 outbreak, indoor air quality monitoring was not a focus area for public facilities such as shopping complexes, hospitals, banks, restaurants, educational institutes, and so forth. However, the rapid spread of this virus and its consequent detrimental impacts have brought indoor air quality into the spotlight. In contrast to outdoor air, indoor air is recycled constantly causing it to trap and build up pollutants, which may facilitate the transmission of virus. There are several monitoring solutions which are available commercially, a typical system monitors the air quality using gas and particle sensors. These sensor readings are compared against well known thresholds, subsequently generating alarms when thresholds are violated. However, these systems do not predict the quality of air for future instances, which holds paramount importance for taking timely preemptive actions, especially for COVID-19 actual and potential patients as well as people suffering from acute pulmonary disorders and other health problems. In this regard, we have proposed an indoor air quality monitoring and prediction solution based on the latest Internet of Things (IoT) sensors and machine learning capabilities, providing a platform to measure numerous indoor contaminants. For this purpose, an IoT node consisting of several sensors for 8 pollutants including NH₃, CO, NO₂, CH₄, CO₂, PM 2.5 along with the ambient temperature & air humidity is developed. For proof of concept and research purposes, the IoT node is deployed inside a research lab to acquire indoor air data. The proposed system has the capability of reporting the air conditions in real-time to a web portal and mobile app through GSM/WiFi technology and generates alerts after detecting anomalies in the air quality. In order to classify the indoor air quality, several machine learning algorithms have been applied to the recorded data, where the Neural Network (NN) model outperformed all others with an accuracy of 99.1%. For predicting the concentration of each air pollutant and thereafter predicting the overall quality of an indoor environment, Long and Short Term Memory (LSTM) model is applied. This model has shown promising results for predicting the air pollutants’ concentration as well as the overall air quality with an accuracy of 99.37%, precision of 99%, recall of 98%, and F1-score of 99%. The proposed solution offers several advantages including remote monitoring, ease of scalability, real-time status of ambient conditions, and portable hardware, and so forth.

Precise estimation of crop yield is crucial for ensuring food security, managing the supply chain, optimally utilizing resources, promoting economic growth, enhancing climate resilience, controlling losses, and mitigating risks in the agricultural industry. Accurate yield prediction depends upon several interactive factors, including crop genotype, climate conditions, soil fertility, sowing & irrigation plan, and crop management practices. For this purpose, remote sensing data and machine learning (ML) algorithms are emerging as indispensable tools that can significantly increase farm productivity while using minimal resources and reducing environmental impact. In this context, the study presents a framework for wheat grain yield prediction using three regression techniques including Random Forest, Xtreme Gradient Boosting (XGB) regression, and Least Absolute Shrinkage & Selection Operator (LASSO) regression. Various aspects of the three models are investigated and results are compared to explore the optimal technique. Drone-based multispectral sensors are employed to acquire data from three wheat experimental fields with three different sowing dates (SD1, SD2, SD3), and the effect of the seeding plan on crop yield is examined. The prediction performance of models is assessed at different growth stages of the crop using several evaluation metrics. The results show that LASSO achieved the highest performance in April with the coefficient of determination (R ² ) of 0.93 and mean absolute error (MAE) of 21.72. The average annual predicted yield is 260.54 g/m ² , 201.64 g/m ² , and 47.29 g/m ² in the wheat field with SD1, SD2, and SD3 respectively. This study can help farmers and agronomists to make informed decisions about crop management activities such as planting & harvest plans, and resource handling.

Wheat is the most important and dominating crop in Pakistan in terms of production and acreage, which is grown on 37% of the cultivated area, accounting for 70% of the total production. However, wheat yield is highly affected by stripe rust, which is considered the most devastating fungal disease, causing 5.5 million tonnes of loss per year globally. In order to minimize this loss, the accurate and timely detection of rust disease is crucial instead of manual inspection. Towards this end, we propose a system to detect wheat rust disease and classify its infection types into four classes, including healthy, resistant, moderate (moderately resistant to moderately susceptible), and susceptible. The wheat rust dataset is collected indigenously from the National Agricultural Research Centre, Islamabad. A pre-trained U2 Net model is used to remove the background and extract the leaf containing the rust disease. Subsequently, two deep learning classifiers, including the Xception model and ResNet-50 are applied to classify the stripe rust severity levels, where the ResNet-50 model outperformed with the highest accuracy of 96%. This research presents a comparison between two state-of-the-art deep learning classifiers in terms of accuracy, memory utilization, and prediction time, which will assist the research community in selecting the most appropriate model for plant disease detection. Moreover, to assess the external validity, the performance of these classifiers is compared with the existing technique using a publicly available dataset, which confirms the validity of the results. Additionally, an intelligent edge computing rust detection device has been developed, where the trained ResNet-50 model is deployed, which facilitates the farmers to monitor the rust attack. The proposed research is aimed to assist the agricultural community to employ preventive measures in a site-specific manner based on the accurate diagnosis of rust disease & its severity, which is intended to improve the quality of the wheat as well as production.

Wheat is a staple crop that is grown across the world due to its substantial contribution to human nutrition. Its significance is evident as it provides almost 20% of calories and protein required for daily human consumption. However, wheat yield is affected by rust disease that can reduce 30% of wheat production which is a serious threat to food security. In order to minimize the loss, it is crucial to identify precisely and localize the wheat rust disease and its infection types. For this purpose, several classification and segmentation techniques are used which are based on machine/deep learning models. This paper provides a realistic analysis and evaluation of various segmentation techniques including Watershed, Grab Cut, and U2-Net. These techniques are applied to the wheat stripe rust data to generate multiple datasets such as Watershed segmented data, GrabCut segmented data, and U2-Net segmented data. Subsequently, a pre-trained deep learning model, ResNet-18 is applied to these datasets to assess the impact of segmentation on classification accuracy. The highest classification accuracy (96.196%) is achieved on the dataset segmented by U2-Net. This research collates several state-of-the-art segmentation techniques in terms of correctness and their direct impact on classification accuracy which gives a pragmatic analysis for researchers to choose optimal segmentation technique. The research primarily focuses on the direct impact of segmentation on classification accuracy of wheat stripe rust, which has not been given sufficient focus in earlier researches.