Monitoring and controlling air quality parameters form an important subject of atmospheric and environmental research today due to the health impacts caused by the different pollutants present in the urban areas. The support vector machine (SVM), as a supervised learning analysis method, is considered an effective statistical tool for the prediction and analysis of air quality. The work presented here examines the feasibility of applying the SVM to predict the ozone and particle concentrations in two Tunisian cities, namely Tunis and Sfax. We used the SVM with the linear kernel, SVM with the polynomial kernel and SVM with the RBF kernel to predict the ozone and particle concentrations in Tunisia for one year. The RBF kernel produced good results for the two pollutants with 0% error rate. Polynomial and linear kernels produced sufficiently low errors for the pollutants, at 9.09% and 18.18%, respectively. Discriminant Analysis (DA) was selected to analyze the datasets of two air quality parameters, namely ozone O3 and Suspended Particles SP. The DA results show that the spatial characterization allows for the successful discrimination between the two cities with an error rate of 4.35% in the case of the linear DA and 0% in the case of the quadratic DA. A thematic map of Tunisia was created using the MapInfo software.

Environmental complexity leads to differences in the spatial distribution of heavy metal pollution in soil and rice. Such spatial differences will seriously affect the safety of planted rice and can impact regional management and control. How to scientifically reveal these spatial differences is an urgent problem. In this study, the spatial mismatch relationship between Cd pollution in soil and rice grains (brown rice) was first explored by the interpolation method. To further reveal the causes of these, the specific recognition rules of the spatial relationship of Cd pollution were extracted based on a decision tree model, and the results were mapped. The results revealed a spatial mismatch in Cd pollution between the soil and rice grains in the study area, and the main results are as follows: (i) slight soil pollution and safe rice accounted for 68.88% of the area; (ii) slight soil pollution and serious rice pollution accounted for 13.39% of the area and (iii) safe soil and serious rice pollution accounted for 11.63% of the area. In addition, 11 recognition rules of Cd spatial pollution relationship between soil and rice were proposed, and the main environmental factors were determined: SOM (soil organic matter), Dis-residence (distance from residential area), soil pH and LAI (leaf area index). The average accuracy of rule recognition was 75.90%. The study reveals the spatial mismatch of heavy metal pollution in soil and crops, providing decision-making references for the spatial accurate identification and targeted prevention of heavy metal pollution spaces.

Long- and short-term exposure to PM2.5 is of great concern in China due to its adverse population health effects. Characteristic of the severity of the situation in China is that in the Jing-Jin-Ji region considered in this work a total of 2725 excess deaths have been attributed to short-term PM2.5 exposure during the period January 10–31, 2013. Technically, the processing of large space-time PM2.5 datasets and the mapping of the space-time distribution of PM2.5 concentrations often constitute high-cost projects. To address this situation, we propose a synthetic modeling framework based on the integration of (a) the Bayesian maximum entropy method that assimilates auxiliary information from land-use regression and artificial neural network (ANN) model outputs based on PM2.5 monitoring, satellite remote sensing data, land use and geographical records, with (b) a space-time projection technique that transforms the PM2.5 concentration values from the original spatiotemporal domain onto a spatial domain that moves along the direction of the PM2.5 velocity spread. An interesting methodological feature of the synthetic approach is that its components (methods or models) are complementary, i.e., one component can compensate for the occasional limitations of another component. Insight is gained in terms of a PM2.5 case study covering the severe haze Jing-Jin-Ji region during October 1–31, 2015. The proposed synthetic approach explicitly accounted for physical space-time dependencies of the PM2.5 distribution. Moreover, the assimilation of auxiliary information and the dimensionality reduction achieved by the synthetic approach produced rather impressive results: It generated PM2.5 concentration maps with low estimation uncertainty (even at counties and villages far away from the monitoring stations, whereas during the haze periods the uncertainty reduction was over 50% compared to standard PM2.5 mapping techniques); and it also proved to be computationally very efficient (the reduction in computational time was over 20% compared to standard mapping techniques).

In this study, we used data from spectroscopic models based on visible and near-infrared (vis-NIR; 350–2500 nm) diffuse reflectance spectroscopy to develop soil maps of polycyclic aromatic hydrocarbons (PAHs) and total toxicity equivalent concentrations (TTEC) of the PAH mixture. The TTEC maps were then used for hazard assessment of three petroleum release sites in the Niger Delta province of Nigeria (5.317°N, 6.467°E). As the paired t-test revealed, there were non-significant (p > 0.05) differences between soil maps of PAH and TTEC developed with chemically measured and vis-NIR-predicted data. Comparison maps of PAH showed a slight to moderate agreement between measured and predicted data (Kappa coefficient = 0.19–0.56). Using proposed generic assessment criteria, hazard assessment showed that the degree of action for site-specific risk assessment and/or remediation is similar for both measurement methods. This demonstrates that the vis-NIR method may be useful for monitoring hydrocarbon contamination in a petroleum release site.

Seagrass meadows are declining at alarming rates globally due to both anthropogenic activities and natural threats. Seagrasses play key ecological roles in coastal ecosystems as primary producers and providers of habitat and environmental structure. Therefore, mapping seagrass beds is indispensable for the effective monitoring and management of coastal vegetated habitats. In contrast to direct sampling techniques and optical remote sensing, active hydroacoustic techniques are relatively inexpensive and efficient for the detection of seagrass. We used a single beam echosounder to detect the spatial and temporal distribution characteristics of the eelgrass Zostera marina L. in an important overwintering habitat for the whooper swan Cygnus cygnus (Swan-Lake lagoon), northern China. We also distinguished echograms of the macroalgae Chaetomorpha linum K. and outlined its threat to seagrass. We also propose a method for calculating the accuracy of interpolation analyses. Results showed that: (1) The distribution of seagrass in Swan Lake varies with seasons, with maximum distribution area in summer. The maximum distribution area of seagrass beds in Swan Lake was 199.09 ha–231.67 ha, accounting for 41.48%–48.26% of the area of Swan Lake; (2) C. linum is a growing threat for seagrass beds of Swan-lake, with distribution area as high as 129.28 ha in May 2018. The invasion and competition by C. linum against seagrass beds could be one of the reasons for the decline in seagrass beds in Swan-Lake; (3) Topo to Raster has the highest interpolation accuracy and is the most conservative among three interpolation methods. Topo to Raster was the most suitable interpolation method for the sonar detection of seagrass beds. The findings may facilitate the application of sonar technology in seagrass monitoring and provide data for the formulation of appropriate seagrass bed management and restoration strategies and policies.

Cystoseira amentacea is a Mediterranean endemic alga thriving on very shallow rocky substrates. It has been considered as a threatened species, having experienced a steady decline and is therefore protected by international conventions. The historical distribution of the species has been assessed along the French Mediterranean coast, on the basis of 467 articles and herbarium vouchers. We have produced an accurate map of its current distribution and abundance along 1832km of coastline, through in situ surveys. C. amentacea was observed along 1125km of shoreline, including 33% of almost continuous or continuous belt. In most of its range, there is no evidence of loss, except in 4 areas of Provence, French Riviera and Corsica. A significant relation was found between the absence or low abundance of C. amentacea and the vicinity of ports and large sewage outfalls. The status of conservation of the species should therefore be reassessed.

Acoustic deterrent devices (ADDs) are used in attempts to mitigate pinniped depredation on aquaculture sites through the emission of loud and pervasive noise. This study quantified spatio-temporal changes in underwater ADD noise detections along western Scotland over 11 years. Acoustic point data (‘listening events’) collected during cetacean line-transect surveys were used to map ADD presence between 2006 and 2016. A total of 19,601 listening events occurred along the Scottish west coast, and ADD presence was recorded during 1371 listening events. Results indicated a steady increase in ADD detections from 2006 (0.05%) to 2016 (6.8%), with the highest number of detections in 2013 (12.6%), as well as substantial geographic expansion. This study demonstrates that ADDs are a significant and chronic source of underwater noise on the Scottish west coast with potential adverse impacts on target (pinniped) and non-target (e.g. cetaceans) species, which requires further study and improved monitoring and regulatory strategies.

Species composition and abundance of dinocysts in relation to environmental factors were studied at 123 stations of surface sediment in Bizerte Lagoon. Forty-eight dinocyst types were identified, mainly dominated by Brigantidinium simplex, Votadinum spinosum, Alexandrium pseudogonyaulax, Alexandrium catenella, and Lingulodinum machaerophorum along with many round brown cysts and spiny round brown cysts. Cysts ranged from 1276 to 20126cystsg−1dry weight sediment. Significant differences in cyst distribution pattern were recorded among the zones, with a higher cyst abundance occurring in the lagoon’s inner areas. Redundancy analyses showed two distinct associations of dinocysts according to location and environmental variables. Ballast water discharges are potential introducers of non-indigenous species, especially harmful ones such as A. catenella and Polysphaeridium zoharyi, with currents playing a pivotal role in cyst distribution. Findings concerning harmful cyst species indicate potential seedbeds for initiation of future blooms and outbreaks of potentially toxic species in the lagoon.

This study investigated the spatial distribution of Alexandrium pseudogonyaulax resting cysts in recently-deposited sediment of Bizerte lagoon (South-Western Mediterranean, Tunisia). This lagoon is the subject of many anthropogenic impacts, such as holding important fishing and aquaculture activities. A. pseudogonyaulax has been shown to produce Goniodomin A, which is a biologically-active compound. We showed that this dinoflagellate produces two types of resting cysts, which could be distinguished by the presence or the absence of a paratabulate wall. The average cyst density across the whole lagoon was rather high, reaching 639cystsg−1 of dry sediment (DS). Cyst densities varied widely among the sampled stations, with the highest density of 1685cystg−1DS being recorded at station 51 near a mussel farm. With respect to sediment characteristics, the highest cyst densities were found within silty sediments with high water content values. The distribution of A. pseudongoyaulax cysts in Bizerte lagoon appears to be related to hydrodynamic factors.

Spatial and temporal patterns of coastal microbial pollution are not well documented. Our study examined these patterns through measurements of fecal indicator bacteria (FIB), nutrients, and physiochemical parameters in Hilo Bay, Hawai'i, during high and low river flow. >40% of samples tested positive for the human-associated Bacteroides marker, with highest percentages near rivers. Other FIB were also higher near rivers, but only Clostridium perfringens concentrations were related to discharge. During storms, FIB concentrations were three times to an order of magnitude higher, and increased with decreasing salinity and water temperature, and increasing turbidity. These relationships and high spatial resolution data for these parameters were used to create Enterococcus spp. and C. perfringens maps that predicted exceedances with 64% and 95% accuracy, respectively. Mapping microbial pollution patterns and predicting exceedances is a valuable tool that can improve water quality monitoring and aid in visualizing FIB hotspots for management actions.