Appling the One-Class Classification Method of Maxent to Detect an Invasive Plant Spartina alterniflora with Time-Series Analysis

Remote sensing monitoring and potential distribution analysis of Spartina alterniflora in coastal zone of Guangxi

In recent years, the continuous expansion of Spartina alterniflora (S. alterniflora) has caused serious damage to coastal wetland ecosystem. Mapping the coverage of S. alterniflora by remote sensing and analyzing its growth pattern pose great importance in controlling the expansion and maintaining the biodiversity of coastal wetlands in Guangxi. This study aimed to use harmonic regression to fit time series data of vegetation indices based on Landsat images, and the phenological features were extracted as the input of random forest model to distinguish S. alterniflora in coastal zone of Guangxi from 2009 to 2020. The influence of natural environmental factors on the distribution of S. alterniflora was evaluated by Maxent model, and the potential distribution was analyzed. The results showed that: (1) Based on the time series data of characteristic indices fitted by harmonic regression, the extraction of phenological features of S. alterniflora identification effect exhibited high accuracy (in the result of 2009, Overall Accuracy [OA] = 97.33%, Kappa = 0.95). (2) During 2009-2020, the S. alterniflora in coastal zone of Guangxi kept proliferating and expanding from east to west. The total area of S. alterniflora continued to increase while the growth rate showed a trend that increased first and then decreased. (3) The Maxent model shows good accuracy in simulating the habitat of S. alterniflora, with a potential distribution area of 14,303.39 hm2. The findings will be beneficial to the understanding of dynamic changes of S. alterniflora in coastal zone of Guangxi and provide a scientific reference for other coastal wetland studies on S. alterniflora expansion.

Global potential distribution of mangroves: Taking into account salt marsh interactions along latitudinal gradients

Mangrove is one of the most productive and sensitive ecosystems in the world. Due to the complexity and specificity of mangrove habitat, the development of mangrove is regulated by several factors. Species distribution models (SDMs) are effective tools to identify the potential habitats for establishing and regenerating the ecosystem. Such models usually include exclusively environmental factors. Nevertheless, recent studies have challenged this notion and highlight the importance of including biotic interactions. Both factors are necessary for a mechanistic understanding of the mangrove distribution in order to promote the protection and restoration of mangroves. Thus, we present a novel approach of combining environmental factors and interactions with salt marsh for projecting mangrove distributions at the global level and within latitudinal zones. To test the salt marsh interaction, we fit the MaxEnt model with two predicting sets: (1) environments only and (2) environments + salt marsh interaction index (SII). We found that both sets of models had good predictive ability, although the SII improved model performance slightly. Potential distribution areas of mangrove decrease with latitudes, and are controlled by biotic and abiotic factors. Temperature, precipitation and wind speed are generally critical at both global scale and ecotones along latitudes. SII is important on global scale, with a contribution of 5.9%, ranking 6th, and is particularly critical in the 10-30°S and 20-30°N zone. Interactions with salt marsh, including facilitation and competition, are shown to affect the distribution of mangroves at the zone of coastal ecotone, especially in the latitudinal range from 10° - 30°. The contribution of SII to mangrove distribution increases with latitudes due to the difference in the adaptive capacity of salt marsh plants and mangroves to environments. Totally, this study identified and quantified the effects of salt marsh on mangrove distribution by establishing the SII. The results not only facilitate to establish a more accurate mangrove distribution map, but also improve the efficiency of mangrove restoration by considering the salt marsh interaction in the mangrove management projects. In addition, the method of incorporating biotic interaction into SDMs through establish the biotic interaction index has contributed to the development of SDMs.

Niche Filling Dynamics of Ragweed (Ambrosia artemisiifolia L.) during Global Invasion

Determining whether the climatic ecological niche of an invasive alien plant is similar to that of the niche occupied by its native population (ecological niche conservatism) is essential for predicting the plant invasion process. Ragweed (Ambrosia artemisiifolia L.) usually poses serious threats to human health, agriculture, and ecosystems within its newly occupied range. We calculated the overlap, stability, unfilling, and expansion of ragweed's climatic ecological niche using principal component analysis and performed ecological niche hypothesis testing. The current and potential distribution of A. artemisiifolia was mapped by ecological niche models to identify areas in China with the highest potential risk of A. artemisiifolia invasion. The high ecological niche stability indicates that A. artemisiifolia is ecologically conservative during the invasion. Ecological niche expansion (expansion = 0.407) occurred only in South America. In addition, the difference between the climatic and native niches of the invasive populations is mainly the result of unpopulated niches. The ecological niche model suggests that southwest China, which has not been invaded by A. artemisiifolia, faces an elevated risk of invasion. Although A. artemisiifolia occupies a climatic niche distinct from native populations, the climatic niche of the invasive population is only a subset of the native niche. The difference in climatic conditions is the main factor leading to the ecological niche expansion of A. artemisiifolia during the invasion. Additionally, human activities play a substantial role in the expansion of A. artemisiifolia. Alterations in the A. artemisiifolia niche would help explain why this species is so invasive in China.

Increased Invasion Risk of Tagetes minuta L. in China under Climate Change: A Study of the Potential Geographical Distributions

Tagetes minuta L., a member of the Tageftes genus belonging to the Asteraceae family, is a well-documented exotic plant native to South America that has become established in China. In this study, 784 occurrence records and 12 environmental variables were used to predict the potential geographical distributions (PGDs) of T. minuta under current and future climatic changes using an optimized MaxEnt model. The results showed that (1) three out of the twelve variables contributed the most to the model performance: isothermality (bio3), precipitation in the driest quarter (bio17), and precipitation in the warmest quarter (bio18); (2) the PGDs of T. minuta under the current climate covered 62.06 × 10⁴ km², mainly in North, South, and Southwest China; and (3) climate changes will facilitate the expansion of the PGDs of T. minuta under three shared socioeconomic pathways (SSP 1-2.6, SSP2-4.5, and SSP5-8.5) in both the 2030s and 2050s. The centroid of suitable habitats under SSP2-4.5 moved the longest distance. T. minuta has the capacity to expand in China, especially in Yunnan, where there exist no occurrence records. Customs, ports, and adjacent regions should strengthen the quarantine of imported goods and mobile personnel for T. minuta, and introduced seedlings should be isolated to minimize their introduction risk.

Effect of freshwater on plant species diversity and interspecific associations in coastal wetlands invaded by Spartina alterniflora

Plant invasions in coastal wetlands lead to the degradation of native vegetation; the introduction of freshwater in coastal wetlands would prevent the spread of invasive plants and facilitate the restoration of native vegetation. In this study, we evaluated the effects of freshwater on plant communities in the coastal wetlands of Yancheng, China, invaded by Spartina alterniflora Loisel. Two field investigations were conducted in 2008 and 2018 before and after the introduction of freshwater (started in 2011). The characteristics of plant communities were subjected to hierarchical cluster analysis and compared using several diversity indices. In addition, differences in habitat community composition and interspecific relationships of dominant species were analyzed. The results showed that S. alterniflora reduced the overall species diversity in the region. Plant species diversity increased after freshwater was introduced into the study site when compared to the areas without freshwater introduction. The introduction of freshwater caused a shift often changes in the interspecific relationships between Suaeda salsa (L.) Pall. and other species. The intensified invasion of S. alterniflora changed the interspecific relationship of native halophytes from negative to positive. Although freshwater effectively inhibited further invasion of S. alterniflora, it also increased the risk of expansion of the glycophytes in the community. The results of this study highlight the need for early intervention for restoration of coastal wetlands, preservation of biodiversity, and management of plant resources.

Predicting the distribution of suitable habitat of the poisonous weed Astragalus variabilis in China under current and future climate conditions

Astragalus variabilis is a locoweed of northwest China that can seriously impede livestock development. However, it also plays various ecological roles, such as wind protection and sand fixation. Here, we used an optimized MaxEnt model to predict the distribution of suitable habitat of A. variabilis under current (1970-2000) conditions and future (2021-2080) climate change scenarios based on recent occurrence records. The most important environmental variables (suitability ranges in parentheses) affecting the distribution of A. variabilis were average maximum temperature of February (-2.12-5.34^°C), followed by total precipitation of June (2.06-37.33 mm), and topsoil organic carbon (0.36-0.69%). The habitat suitability of A. variabilis was significantly correlated with the frequency of livestock poisoning (p < 0.05). Under current climate conditions, the suitable environment of A. variabilis was distributed in central and western Inner Mongolia, Ningxia, central and northwestern Gansu, central and northwestern Qinghai, and the four basins around the Tianshan Mountains in Xinjiang. Under future climate conditions, the suitable habitat of A. variabilis shifted to higher latitudes and altitudes. No previous studies have used niche models to predict the suitable environment of this species nor analyzed the relationship between the habitat suitability of poisonous plants and the frequency of animal poisoning. Our findings provide new insights that will aid the prevention of livestock animal poisoning and the control of poisonous plants, promote the development of the livestock husbandry industry, and provide basic information that will facilitate the maintenance of the ecological balance of grassland ecosystems.

Ecological Niche Shifts Affect the Potential Invasive Risk of Rapistrum rugosum (L.) All. in China

Ecological niche is a key concept that links species distributions. Ecological niche shifts are expected to affect the potential invasive risk of alien species. Rapistrum rugosum is an invasive agricultural weed in many countries. Wild populations of R. rugosum have been recorded in China, representing a great threat to the regional crops. Based on distribution records from different regions and relevant environmental variables, the present study predicted the potential distribution and estimated the invasive risk of R. rugosum in China. Ecological niche shifts strongly affected the potential invasive risk of R. rugosum in China. The two most important variables were annual temperature range (Bio7) and mean temperature of the coldest quarter (Bio11). The total suitable habitat for the species covered an area of 287.53 × 10⁴km² and was mainly distributed in Southwest, Southeast, and Central China. Australia, Canada, Brazil, the United States, and Argentina accounted for over 90% of the inspection records of R. rugosum from Chinese entry ports during 2015-2018. The intercepted R. rugosum was frequently mixed in Glycine max (L.) Merr., Hordeum vulgare L., linseed, Triticum aestivum L., and Sorghum bicolor (L.) Moench. Moreover, 80% interceptions were recorded from Tianjin, Guangdong, Nanjing, and Chengdu customs. Climatic conditions do not limit the establishment capability of R. rugosum in China. Our results provide a theoretical reference for the development of monitoring and control measures for this invasive weed.

Learning to Classify DWDM Optical Channels from Tiny and Imbalanced Data

Applying machine learning algorithms for assessing the transmission quality in optical networks is associated with substantial challenges. Datasets that could provide training instances tend to be small and heavily imbalanced. This requires applying imbalanced compensation techniques when using binary classification algorithms, but it also makes one-class classification, learning only from instances of the majority class, a noteworthy alternative. This work examines the utility of both these approaches using a real dataset from a Dense Wavelength Division Multiplexing network operator, gathered through the network control plane. The dataset is indeed of a very small size and contains very few examples of “bad” paths that do not deliver the required level of transmission quality. Two binary classification algorithms, random forest and extreme gradient boosting, are used in combination with two imbalance handling methods, instance weighting and synthetic minority class instance generation. Their predictive performance is compared with that of four one-class classification algorithms: One-class SVM, one-class naive Bayes classifier, isolation forest, and maximum entropy modeling. The one-class approach turns out to be clearly superior, particularly with respect to the level of classification precision, making it possible to obtain more practically useful models.

An eco-parametric method to derive sedimentation rates for coastal saltmarshes

The saltmarsh plant Spartina alterniflora was introduced to the Jiangsu coasts, China and serves as an ecological engineer to reduce near-bed shear stress, trap fine-grained sediments and protect the coast from wave-induced erosion. The saltmarshes thus could record the Spartina colonization-driven changes within the sedimentary layers. Based on these ecological and sedimentological changes in sediments, we present a new eco-parametric method to estimate the sedimentation rate for the newly-formed wetlands in the Yancheng Wetland Nature Reserve for Rare Birds, Jiangsu. Sediment cores and satellite imagery were used to identify the thickness of accumulated sediment layers and the time since the Spartina colonization. We defined the original ground on which Spartina alterniflora initially colonized using pigment concentrations, grain size and stable carbon isotopic compositions of organic matter (δ¹³C) in sediments. We also determined the time mark of the Spartina colonization by examining the Landsat images over 1982-2018 to discriminate the Spartina alterniflora from other native plants and geomorphological features. These two datasets yielded a sedimentation rate of 3.3 cm/yr for Core A and of 9.6 cm/yr for Core B, the latter evidenced by an increase of ~ 0.51 m in the bed level from 2008 to 2014. Combining the ²¹⁰Pb dating method, we further estimated the sedimentation rate for the layers beneath the original ground, which was comparable to that of the bare flats in the Jiangsu coast. Even though this new method is only applicable to newly-formed saltmarshes, it helps identify the recent sedimentation events as well as reveal the environmental changes and the evolution of saltmarsh-bare flat systems due to the interplay between vegetation, hydrodynamics and sediment dynamics. It thus could be an efficient and cost-effective tool for an improved understanding of the response of coastal wetlands to a changing climate/environment.

Mapping an Invasive Plant Spartina alterniflora by Combining an Ensemble One-Class Classification Algorithm with a Phenological NDVI Time-Series Analysis Approach in Middle Coast of Jiangsu, China

Spartina alterniflora (S. alterniflora) is one of the worst plant invaders in the coastal wetlands of China. Accurate and repeatable mapping of S. alterniflora invasion is essential to develop cost-effective management strategies for conserving native biodiversity. Traditional remote-sensing-based mapping methods require a lot of fieldwork for sample collection. Moreover, our ability to detect this invasive species is still limited because of poor spectral separability between S. alterniflora and its co-dominant native plants. Therefore, we proposed a novel scheme that uses an ensemble one-class classifier (EOCC) in combination with phenological Normalized Difference Vegetation Index (NDVI) time-series analysis (TSA) to detect S. alterniflora. We evaluated the performance of the EOCC algorithm in two scenarios, i.e., single-scene analysis (SSA) and NDVI-TSA in the core zones of Yancheng National Natural Reserve (YNNR). Meanwhile, a fully supervised classifier support vector machine (SVM) was tested in the two scenarios for comparison. With these scenarios, the crucial phenological stages and the advantage of phenological NDVI-TSA in S. alterniflora recognition were also investigated. Results indicated the EOCC using only positive training data performed similarly well with the SVM trained on complete training data in the YNNR. Moreover, the EOCC algorithm presented a more robust transferability with notably higher classification accuracy than the SVM when being transferred to a second site, without a second training. Furthermore, when combined with the phenological NDVI-TSA, the EOCC algorithm presented more balanced sensitivity–specificity result, showing slightly better transferability than it performed in the best phenological stage (i.e., senescence stage of November). The achieved results (overall accuracy (OA), Kappa, and true skill statistic (TSS) were 92.92%, 0.843, and 0.834 for the YNNR, and OA, Kappa, and TSS were 90.94%, 0.815, and 0.825 for transferability to the non-training site) suggest that our detection scheme has a high potential for the mapping of S. alterniflora across different areas, and the EOCC algorithm can be a viable alternative to traditional supervised classification method for invasive plant detection.

A multiscale approach to identifying spatiotemporal pattern of habitat selection for red-crowned cranes

Effective conservation measures largely depend on knowledge of habitat selection of target species. Little is known about the scale characteristics and temporal rhythm of habitat selection of the endangered red-crowned crane, limiting the habitat conservation. Here, two red-crowned cranes were tracked with Global position system (GPS) for two years in Yancheng National Nature Reserve (YNNR). A multiscale approach was developed to identify the spatiotemporal pattern of habitat selection of red-crowned cranes. The results revealed that Red-crowned cranes preferred to select Scirpus mariqueter, ponds, Suaeda salsa, and Phragmites australis, and avoid Spartina alterniflora. In each season, habitat selection ratio for Scirpus mariqueter and ponds was the highest during the day and night, respectively. Further multiscale analysis showed that the percent coverage of Scirpus mariqueter at the 200-m to 500-m scale was the most important predictor for all habitat selection modeling, emphasizing the importance of restoring a large area of Scirpus mariqueter habitat for red-crowned crane population restoration. Additionally, other variables affect habitat selection at different scales, and their contributions vary with seasonal and circadian rhythm. Furthermore, habitat suitability was mapped to provide a direct basis for habitat management. The suitable area of daytime and nighttime habitat accounted for 5.4%-19.0% and 4.6%-10.2% of the study area, respectively, implying the urgency of restoration. The study highlighted the scale and temporal rhythms of habitat selection for various endangered species that depend on small habitats. The proposed multiscale approach applies to the restoration and management of habitats of various endangered species.