Spatiotemporal system forecasting with irregular time steps via masked autoencoder

Robust multivariate time series forecasting is crucial in many cyberphysical and Internet of Things applications. Existing state-of-the-art robust forecasting models decompose time series into independent functions covering trends and periodicities. However, these independent functions fail to capture correlations among multiple time series, thereby reducing prediction accuracy. Moreover, existing robust forecasting models treat certain abrupt but normal changes, e.g., caused by holidays, as outliers because they occur infrequently and have data distributions that resemble those of outliers. This exacerbates model bias and reduces prediction accuracy. This paper aims to capture correlations across multiple time series and abrupt but normal changes, thereby improving prediction accuracy. We employ weak labels to partition the dataset into source and target domains. Then, we propose the Domain Adversarial Robust Forecaster (DARF). This forecasting model is based on adversarial domain adaptation and includes two novel modules: Correlated Robust Forecaster (CORF) and Domain Critic. Specifically, CORF constitutes an encoder-decoder framework proficient at robust multivariate time series forecasting, and Domain Critic works to reduce data bias. Extensive experiments and discussions show that DARF is capable of state-of-the-art forecasting accuracy.

We reviewed the current key techniques of portable mass spectrometer and discussed its application in environmental monitoring. At present, mass spectrometer has two development directions. One direction is high-throughputs, high-sensitivity and high-resolution laboratory mass spectrometer. The other is small, in-situ monitoring portable mass spectrometer. With the rapid development of electronic technology and new materials, portable mass spectrometers are widely used in environmental pollution monitoring because they have the advantages of small size, light weight and low power consumption.

The use of hyperspectral reflectance and transmittance data, as well as advanced machine learning approaches, has substantially improved material analysis by expanding into the near-infrared (NIR) and shortwave infrared (SWIR) areas beyond the visible spectrum. This study looks into fresh green tea leaves’ SWIR-2 region (2001–2500 nm), which is important for materials science, agriculture, and environmental monitoring applications. While hyperspectral data contains abundant and detailed information, its complexity and high dimensionality pose difficulties for precise analysis. We use deep learning methods, particularly convolutional neural networks (CNNs)-based dual-input/output (Dual-Net), to address these issues by refining spectral signatures and improving prediction accuracy across a variety of applications. Our method accounts for spectral dependencies, improving the accuracy of predictions concerning leaf attributes like water content, nitrogen and chlorophyll concentrations, and other biophysical properties, even under complex environmental conditions. The findings show that deep learning models make effective use of SWIR-2 spectra for important evaluations of plant health. The proposed method produced mean (±SD) root-mean-square errors (RMSEs) of 0.012 (±0.012) of reflectance and 0.011 (±0.010) of transmittance for individual spectra, and RMSEs of 0.028 (±0.029) of reflectance and 0.022 (±0.023) of transmittance for SWIR-2 bands. This method shows strong potential for advancing remote sensing applications, particularly in monitoring plant health and productivity. Further improvements could be realized through the development of a more comprehensive green leaf spectral database.

The quality of water, air, and soil has significantly deteriorated, and the physiological processes of organisms have been affected due to negligent human activities, such as the direct discharge of industrial waste into the environment. Cyclodextrin derivatives are emerging as sensor probes for detecting environmentally threatened pollutants. The disclosed CD-based adsorbents exhibit high adsorption efficiency for various pollutants. The hydrophobic cavity in cyclodextrins (CDs) is also crucial in capturing organic contaminants. The unique cavity structure of cyclodextrin has been utilised to detect pollutants through CD-based molecules, enabling self-assembly. Cyclodextrins enhance the detection sensitivity of sensors that rely on electrochemical detection, surface acoustic waves, Raman scattering, luminescence, or fluorescence. It also discusses the wide range of contaminants in various industries, including pharmaceutical, textile, and chemical industries. This review explores the recent advancements in cyclodextrin-based sensor design and their potential applications in environmental monitoring.

This article presents a review of many types of SERS sensors for food safety and environmental pollution monitoring based on detecting rhodamine. It introduces the basic concepts of substrates, enhancement factors, and mechanisms, devices’ sensors integrated with the microstructure. Here, we review the state-of-the-art research in the field of rhodamine monitoring and highlight the applications of SERS sensors. The trends in the development of substrates for different applications have been mentioned with the aim of providing an overview of the development of different SERS substrates. Thus, an efficient approach for rhodamine detection has a good perspective for application in environmental monitoring.

The demand for rapid, portable, and cost-effective analytical tools has driven advances in smartphone-based microfluidic sensors. By combining microfluidic precision with the accessibility and processing power of smartphones, these devices offer real-time and on-site diagnostic capabilities. This review explores recent developments in smartphone-integrated microfluidic sensors, focusing on their design, fabrication, smartphone integration, and analytical functions with the applications in forensic science, agriculture, and environmental monitoring. In forensic science, these sensors provide fast, field-based alternatives to traditional lab methods for detecting substances like DNA, drugs, and explosives, improving investigation efficiency. In agriculture, they support precision farming by enabling on-demand analysis of soil nutrients, water quality, and plant health, enhancing crop management. In environmental monitoring, these sensors allow the timely detection of pollutants in air, water, and soil, enabling quicker responses to hazards. Their portability and user-friendliness make them particularly valuable in resource-limited settings. Overall, this review highlights the transformative potential of smartphone-based microfluidic sensors in enabling accessible, real-time diagnostics across multiple disciplines.

The natural environment is essential for human survival and development since it provides water resources, land resources, biological resources and climate resources etc. As a developing country, China has witnessed a significant change in the natural environment in recent decades; and therefore, monitoring and mastering the status of the environment is of great significance. Due to the characteristics of large-scale and dynamic observation, remote sensing technology has been an indispensable approach for environmental monitoring. This paper reviews the satellite resources, institutions and policies for environmental monitoring in China, and the advances in research and application of remote sensing from five aspects: ecological index retrieval, environmental monitoring in protected areas, rural areas, urban areas and mining areas. The remote sensing models and methods for various types of environmental monitoring, and the specific applications in China are comprehensively summarized. This paper also points out major challenges existing at the current stage: satellite sensor problems, integrated use challenges of datasets, uncertainty in the retrieval process of ecological variables, scaling effect problems, a low degree of automation, the weak ability of forecasting and comprehensive analysis, and a lack of computational power for massive datasets. Finally, the development trend and future directions are put forward to direct the research and application of environmental monitoring and protection in the new era.

The continuously rising interest in chemical sensors’ applications in environmental monitoring, for soil analysis in particular, is owed to the sufficient sensitivity and selectivity of these analytical devices, their low costs, their simple measurement setups, and the possibility to perform online and in-field analyses with them. In this review the recent advances in chemical sensors for soil analysis are summarized. The working principles of chemical sensors involved in soil analysis; their benefits and drawbacks; and select applications of both the single selective sensors and multisensor systems for assessments of main plant nutrition components, pollutants, and other important soil parameters (pH, moisture content, salinity, exhaled gases, etc.) of the past two decades with a focus on the last 5 years (from 2017 to 2021) are overviewed.

Cheese-making traits in dairy cattle are important to the dairy industry but are difficult to measure at the individual level because there are limitations on collecting phenotypic information. Mid-infrared spectroscopy has its advantages, but it can only be used during monthly milk recordings. Recently, in-line devices for real-time analysis of milk quality have been developed. The AfiLab recording system (Afimilk) offers significant benefits as phenotypes can be collected from each cow at each milking session. The objective of this study was to assess the potential of integrating AfiLab real-time milk analyzer measures with the stacking ensemble learning technique using heterogeneous base learners for the in-line daily monitoring of cheese-making traits in Holstein cattle with a view to developing a precision livestock farming system for monitoring the technological quality of milk. Data and samples for wet-laboratory analyses were collected from 499 Holstein cows belonging to 2 farms where the AfiLab system was installed. The traits of concern were 9 milk coagulation traits [3 milk coagulation properties (MCP), and 6 curd firming traits (CFt)], and 7 cheese-making traits [3 cheese yield (CY) traits, and 4 milk nutrient recovery in the curd (REC) traits]. The near-infrared AfiLab spectral data and on-farm information (days in milk and parity) were used to assess the predictive ability of different statistical methods [elastic net (EN), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), and artificial neural network (ANN)] across different cross-validation scenarios. These statistical methods were considered the base learners, which were then combined in a stacking ensemble learning. Results indicate that including information on the cows (days in milk and parity) in the AfiLab infrared prediction increased its accuracy by 10.3% for traditional MCP, 13.8% for curd firming, 9.8% for CY, and 11.2% for REC traits compared with those obtained from near-infrared AfiLab alone. The statistical approaches exhibited high prediction accuracies (R2) averaged across the cross-validation scenarios for traditional MCP (0.58 for ANN, 0.55 for EN and GBM, 0.52 for XGBoost, and 0.62 for stacking ensemble), CFt (0.55 for ANN, 0.54 for EN and GBM, 0.53 for XGBoost, and 0.61 for stacking ensemble), and similar R2 averages for CY and REC (0.55 for ANN, 0.54 for EN and GBM, 0.53 for XGBoost, and 0.61 for stacking ensemble). The ANN approach was more accurate than the other base learners (EN, GBM, and XGBoost) and improved accuracy across cross-validation scenarios on average by 7% for traditional MCP, 5% for CFt, 8% for CY, and 7% for REC. The stacking ensemble method improved prediction accuracy by 3% to 31% for traditional MCP, 2% to 26% for CFt, 1% to 38% for CY traits, and 2% to 27% for REC traits compared with the base learners. The prediction accuracies of the different approaches evaluated tended to decrease from the 10-fold cross-validation to the independent validation scenario, although there was a smaller reduction in prediction accuracy with the stacking ensemble learning technique across all the cross-validation scenarios. Our results show that combining in-line on-farm information with stacking ensemble machine learning represents an effective alternative for obtaining robust daily predictions of milk cheese-making traits.

Chapter 29 - Molecular imprinted biosensors

The convergence of microfluidic and electrochemical biosensor technologies offers significant potential for rapid, in‐field diagnostics in biomedical and environmental applications. Traditional systems face challenges in cost, scalability, and operational complexity, especially in remote settings. Addressing these issues, laser‐induced graphene microfluidic integrated sensors (LIGMIS) are presented as an innovative platform that integrates microfluidics and electrochemical sensors both comprised of laser‐induced graphene. This study advances the LIGMIS concept by resolving issues of uneven fluid transport, increased hydrophobicity during storage, and sensor biofunctionalization challenges. Key innovations include Y‐shaped reservoirs for consistent fluid flow, hydrophilic polyethyleneimine coatings to maintain wettability, and separable microfluidic and electrochemical components enabling isolated electrode nanoparticle metallization and biofunctionalization. Multiplexed electrochemical detection of the neonicotinoid imidacloprid and nitrate ions in environmental water samples yields detection limits of 707 nm and 10−5.4 m with wide sensing ranges of 5–100 µm and 10−5–10−1 m, respectively. Similarly, uric acid and calcium ions are detected in saliva, demonstrating detection limits of 217 nm and 10−5.3 m with sensing ranges of 10–50 µm, and 10−5–10−2.5 m, respectively. Overall, this biosensing demonstrates the capability of the LIGMIS platform for multiplexed detection in biologically complex solutions, with applications in environmental water quality monitoring and oral cancer screening.

The rapid urbanization of modern cities has necessitated the adoption of intelligent systems to optimize resource allocation, enhance public services, and improve overall urban living standards. Artificial Intelligence (AI)-driven predictive analytics has emerged as a pivotal tool in smart city development, enabling data-driven decision-making for traffic management, energy distribution, healthcare, and public safety. However, traditional centralized AI models face significant challenges, including data privacy risks, security vulnerabilities, and scalability limitations. This paper introduces an AI-Powered Predictive Analytics Framework (AIPAF) that integrates Federated Learning (FL) and Blockchain Security to overcome these challenges. Federated Learning enables collaborative model training across distributed edge devices without requiring raw data exchange, thereby preserving privacy and reducing communication overhead. Blockchain technology ensures data integrity, transparency, and tamper-proof model updates through decentralized consensus mechanisms. Experimental evaluations demonstrate that AIPAF achieves a 32% improvement in predictive accuracy, a 40% reduction in data transmission costs, and a 28% enhancement in privacy compliance compared to conventional cloud-based AI systems. Additionally, blockchain integration reduces unauthorized data access incidents by 45%, establishing a secure and auditable environment for AI-driven urban analytics. The framework’s scalability is validated across diverse smart city applications, including traffic optimization, energy efficiency, and environmental monitoring. This study underscores the transformative potential of combining Federated Learning and Blockchain to create a secure, privacy-preserving, and scalable AI infrastructure for smart cities. The findings highlight the framework’s ability to address critical challenges in urban AI deployments while ensuring regulatory compliance and operational efficiency.

Smartphone-based colorimetric sensing with reference calibration and ensemble machine learning for enhanced detection of nitrite and ammonium ions.

Abstract

This chapter presents some considerations related to the applications in environment monitoring of some concepts as: estimation, fault detection and diagnosis, theory of distributed parameter systems and artificial intelligence based on the modern technology of wireless sensor networks. All these concepts allow treatment of large, complex, non-linear and multivariable system of the environment by learning and extrapolation. The environment may be seen as a complex ensemble of different distributed parameter systems, described with partial differential equations. Sensor networks (Akyildiz & all, 2002) have large and successful applications in monitoring the environment, they been capable to measure, as a distributed sensor, the physical variables, on a large area, which are characterizing the environment, and also to communicate at long distance the measured values, from the distributed parameter environmental processes. A lot of papers and books have been published in the fields of using sensor networks in environment monitoring in the last years. Some related work is surveyed as follows. The paper (Cuiyun & all., 2006) presents some research consideration related the changes of urban spatial thermal environment, for sustainable urban development, to improve the quality of human habitation environment. The urban thermal phenomenon is revealed using thermal remote sensing imagery, based on the instantaneous radiant temperature of the land surfaces. An architecture of sensor network for environment is presented in (Lan & all, 2008). Environmental pollution and meteorological processes may be studied using various kinds of environmental sensor networks. The modern intelligent sensor networks comprise automatic sensor nodes and communication systems which communicate their data to a sensor network server, where these data are integrated with other environmental information. The paper (Giannopoulos & all, 2009) presents the design and implementaion of a wireless sensor network for monitoring environmental variables and evaluates its effectiveness. It has application in environment variable monitoring such as: temperature, humidity, barometric pressure, soil moisture and ambient light, for research in agriculture, habitat monitoring, weather monitoring and so on. In order to improve the capacity of the environmental sensor networks different techniques may be used. The paper (Talukder & all, 2008) is using a model predictive control for optimal resource management in environment sensor networks, for with application at spatiotemporal events of a coastal monitoring and forecast system. The paper (Dardari & all, 2007)