Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Meta-analysis of engineered nanoparticles dynamic aggregation in freshwater-like systems using machine learning techniques.

In Journal of environmental management

Predictive algorithms for exposure characterization of engineered nanoparticles (ENPs) in the ecosystems are essential to improve the development of robust nano-safety frameworks. Here, machine learning (ML) techniques were utilised for data mining and prediction of the dynamic aggregation transformation process in aqueous environments using case studies of nZnO and nTiO2. Supervised ML models using input variables of natural organic matter, ionic strength, size, and ENPs concentration showed poor prediction performance based on statistical metric values of root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), and Nash-Sutcliffe efficiency (NSE) for both types of ENP. On the contrary, algorithms developed using model input parameters of zeta potential, pH, and time had good generalisation and high prediction accuracy. Among the five developed ML algorithms, random forest regression, support vector regression, and artificial neural network generated good prediction accuracy for both data sets. Therefore, the use of ML can be valuable in the development of robust nano-safety frameworks to optimise societal benefits, and for proactive long-term ecological protection.

Yalezo Ntsikelelo, Musee Ndeke

2023-Mar-17

Aggregation, Aqueous system, Hydrodynamic diameter, Machine learning, Meta-analysis, Nanoparticles transformation

General General

Nature dependent tourism - Combining big data and local knowledge.

In Journal of environmental management

The ability to quantify nature's value for tourism has significant implications for natural resource management and sustainable development policy. This is especially true in the Eastern Caribbean, where many countries are embracing the concept of the Blue Economy. The utilization of user-generated content (UGC) to understand tourist activities and preferences, including the use of artificial intelligence and machine learning approaches, remains at the early stages of development and application. This work describes a new effort which has modelled and mapped multiple nature dependent sectors of the tourism industry across five small island nations. It makes broad use of UGC, while acknowledging the challenges and strengthening the approach with substantive input, correction, and modification from local experts. Our approach to measuring the nature-dependency of tourism is practical and scalable, producing data, maps and statistics of sufficient detail and veracity to support sustainable resource management, marine spatial planning, and the wider promotion of the Blue Economy framework.

Spalding Mark D, Longley-Wood Kate, McNulty Valerie Pietsch, Constantine Sherry, Acosta-Morel Montserrat, Anthony Val, Cole Aaron D, Hall Giselle, Nickel Barry A, Schill Steven R, Schuhmann Peter W, Tanner Darren

2023-Mar-17

Blue economy, Eastern caribbean, Ecosystem services, Nature dependent tourism, User-generated content, Wildlife tourism

General General

Spatially explicit modeling of disease surveillance in mixed oak-hardwood forests based on machine-learning algorithms.

In Journal of environmental management

Incidences of disease, dieback, decline or mortality, some of which induced or enhanced by climate change, threaten the sustainability of forest stands in many ecosystems. Spatially explicit prediction of disease onset remains challenging, however, due to the involvement of several causative agents. In this paper, we developed a generic framework based on machine-learning algorithms and spatial analyses for landscape-level prediction of oak disease outbreaks caused by the charcoal fungus Biscogniauxia mediterranea in a mixed-oak forest of Mediterranean climate. For prediction, we used a set of fifteen causative factors as a cross-function of soil, site and stand-related predictors. A total of 80 sample plots, including 1134 affected trees, were surveyed and used for the modeling process at the 5600-ha landscape level of the southern Zagros, Iran, where the disease occurs in roughly 25% of forest lands. Ten machine learning algorithms were explored and the performance of each algorithm to predict oak disease outbreak was evaluated. The modeling framework used maximum entropy to remove the least influential variables and build the status-quo management scenario to which the results of the prediction models were compared. Results showed that the random forests algorithm (AUC = 0.96: Precision = 0.71: Accuracy = 0.90: F-Measure = 0.70) achieved significantly better results than the status-quo management (Precision = 0.13: Accuracy = 0.67: F-Measure = 0.12) and any other algorithm. Soil chemical properties (NPK, organic carbon and EC) and landform predictors (slope, distance to roads, and TWI) were major forecasters of oak disease outbreak identified by the random forest algorithm. Geostatistical analysis enabled the creation of a map that identified sites at higher risk of infestation, allowing epidemiologists and forest managers to find sites likely to be infested. Consequently, financial resources can be allocated and management practices such as sanitation felling treatments applied across large forest landscapes to minimize the risk of spread and severity to uninfested high-value trees on nearby or adjacent land zones that are in the early stage of epidemics.

Ezzati Sättar, Zenner Eric K, Pakdaman Morteza, Naseri Mohammad Hassan, Nikjoui Marzieh, Ahmadi Shahram

2023-Mar-17

Conservation, Data science, Oak dieback, Quercus brantii, Spatial planning, Statistical analysis

General General

Oil spills detection from SAR Earth observations based on a hybrid CNN transformer networks.

In Marine pollution bulletin

Oil spills are the main threats to marine and coastal environments. Due to the increase in the marine transportation and shipping industry, oil spills have increased in recent years. Moreover, the rapid spread of oil spills in open waters seriously affects the fragile marine ecosystem and creates environmental concerns. Effective monitoring, quick identification, and estimation of the volume of oil spills are the first and most crucial steps for a successful cleanup operation and crisis management. Remote Sensing observations, especially from Synthetic Aperture Radar (SAR) sensors, are a very suitable choice for this purpose due to their ability to collect data regardless of the weather and illumination conditions and over far and large areas of the Earth. Owing to the relatively complex nature of SAR observations, machine learning (ML) based algorithms play an important role in accurately detecting and monitoring oil spills and can significantly help experts in faster and more accurate detection. This paper uses SAR images from ESA's Copernicus Sentinel-1 satellite to detect and locate oil spills in open waters under different environmental conditions. To this end, a deep learning framework has been presented to identify oil spills automatically. The SAR images were segmented into two classes, the oil slick and the background, using convolutional neural networks (CNN) and vision transformers (ViT). Various scenarios for the proposed architecture were designed by placing ViT networks in different parts of the CNN backbone. An extensive dataset of oil spill events in various regions across the globe was used to train and assess the performance of the proposed framework. After the detection performance assessments, the F1-score values for the standard DeepLabV3+, FC-DenseNet, and U-Net networks were 75.08 %, 73.94 %, and 60.85, respectively. In the combined networks models (combination of CNN and ViT), the best F1-score results were obtained as 78.48 %. Our results showed that these hybrid models could improve detection accuracy and have a high ability to distinguish oil spill borders even in noisy images. Evaluation metrics are increased in all the combined networks compared to the original CNN networks.

Dehghani-Dehcheshmeh Saeid, Akhoondzadeh Mehdi, Homayouni Saeid

2023-Mar-17

Deep convolutional neural networks, Oil spill detection, Synthetic aperture radar, Vision transformers

Public Health Public Health

PCR-like performance of rapid test with permselective tunable nanotrap.

In Nature communications ; h5-index 260.0

Highly sensitive rapid testing for COVID-19 is essential for minimizing virus transmission, especially before the onset of symptoms and in asymptomatic cases. Here, we report bioengineered enrichment tools for lateral flow assays (LFAs) with enhanced sensitivity and specificity (BEETLES2), achieving enrichment of SARS-CoV-2 viruses, nucleocapsid (N) proteins and immunoglobulin G (IgG) with 3-minute operation. The limit of detection is improved up to 20-fold. We apply this method to clinical samples, including 83% with either intermediate (35%) or low viral loads (48%), collected from 62 individuals (n = 42 for positive and n = 20 for healthy controls). We observe diagnostic sensitivity, specificity, and accuracy of 88.1%, 100%, and 91.9%, respectively, compared with commercial LFAs alone achieving 14.29%, 100%, and 41.94%, respectively. BEETLES2, with permselectivity and tunability, can enrich the SARS-CoV-2 virus, N proteins, and IgG in the nasopharyngeal/oropharyngeal swab, saliva, and blood serum, enabling reliable and sensitive point-of-care testing, facilitating fast early diagnosis.

Park Seong Jun, Lee Seungmin, Lee Dongtak, Lee Na Eun, Park Jeong Soo, Hong Ji Hye, Jang Jae Won, Kim Hyunji, Roh Seokbeom, Lee Gyudo, Lee Dongho, Cho Sung-Yeon, Park Chulmin, Lee Dong-Gun, Lee Raeseok, Nho Dukhee, Yoon Dae Sung, Yoo Yong Kyoung, Lee Jeong Hoon

2023-Mar-18

Public Health Public Health

PCR-like performance of rapid test with permselective tunable nanotrap.

In Nature communications ; h5-index 260.0

Highly sensitive rapid testing for COVID-19 is essential for minimizing virus transmission, especially before the onset of symptoms and in asymptomatic cases. Here, we report bioengineered enrichment tools for lateral flow assays (LFAs) with enhanced sensitivity and specificity (BEETLES2), achieving enrichment of SARS-CoV-2 viruses, nucleocapsid (N) proteins and immunoglobulin G (IgG) with 3-minute operation. The limit of detection is improved up to 20-fold. We apply this method to clinical samples, including 83% with either intermediate (35%) or low viral loads (48%), collected from 62 individuals (n = 42 for positive and n = 20 for healthy controls). We observe diagnostic sensitivity, specificity, and accuracy of 88.1%, 100%, and 91.9%, respectively, compared with commercial LFAs alone achieving 14.29%, 100%, and 41.94%, respectively. BEETLES2, with permselectivity and tunability, can enrich the SARS-CoV-2 virus, N proteins, and IgG in the nasopharyngeal/oropharyngeal swab, saliva, and blood serum, enabling reliable and sensitive point-of-care testing, facilitating fast early diagnosis.

Park Seong Jun, Lee Seungmin, Lee Dongtak, Lee Na Eun, Park Jeong Soo, Hong Ji Hye, Jang Jae Won, Kim Hyunji, Roh Seokbeom, Lee Gyudo, Lee Dongho, Cho Sung-Yeon, Park Chulmin, Lee Dong-Gun, Lee Raeseok, Nho Dukhee, Yoon Dae Sung, Yoo Yong Kyoung, Lee Jeong Hoon

2023-Mar-18