Abstract. How to effectively describe ecological patterns in nature over broader spatial scales and build a modeling ecological framework has become an important issue in ecological research. We test four modeling methods (MAXENT, DOMAIN, GLM and ANN) to predict the potential habitat of Schima superba (Chinese guger tree, CGT) with different spatial scale in the Huisun study area in Taiwan. Then we created three sampling design (from small to large scales) for model development and validation by different combinations of CGT samples from aforementioned three sites (Tong-Feng watershed, Yo-Shan Mountain, and Kuan-Dau watershed). These models combine points of known occurrence and topographic variables to infer CGT potential spatial distribution. Our assessment revealed that the method performance from highest to lowest was: MAXENT, DOMAIN, GLM and ANN on small spatial scale. The MAXENT and DOMAIN two models were the most capable for predicting the tree's potential habitat. However, the outcome clearly indicated that the models merely based on topographic variables performed poorly on large spatial extrapolation from Tong-Feng to Kuan-Dau because the humidity and sun illumination of the two watersheds are affected by their microterrains and are quite different from each other. Thus, the models developed from topographic variables can only be applied within a limited geographical extent without a significant error. Future studies will attempt to use variables involving spectral information associated with species extracted from high spatial, spectral resolution remotely sensed data, especially hyperspectral image data, for building a model so that it can be applied on a large spatial scale.
Up to 16-dB of gross gain at a wavelength of 1.47 /spl mu/m was achieved by a broadband Cr/sup 4+/:YAG fiber amplifier. The simulation indicates that the minimum noise figure is close to 3-dB at 1.24-1.6 /spl mu/m range.
Abstract. The prediction of species distribution has become a focus in ecology. For predicting a result more effectively and accurately, some novel methods have been proposed recently, like support vector machine (SVM) and maximum entropy (MAXENT). However, high complexity in the forest, like that in Taiwan, will make the modeling become even harder. In this study, we aim to explore which method is more applicable to species distribution modeling in the complex forest. Castanopsis carlesii (long-leaf chinkapin, LLC), growing widely in Taiwan, was chosen as the target species because its seeds are an important food source for animals. We overlaid the tree samples on the layers of altitude, slope, aspect, terrain position, and vegetation index derived from SOPT-5 images, and developed three models, MAXENT, SVM, and decision tree (DT), to predict the potential habitat of LLCs. We evaluated these models by two sets of independent samples in different site and the effect on the complexity of forest by changing the background sample size (BSZ). In the forest with low complex (small BSZ), the accuracies of SVM (kappa = 0.87) and DT (0.86) models were slightly higher than that of MAXENT (0.84). In the more complex situation (large BSZ), MAXENT kept high kappa value (0.85), whereas SVM (0.61) and DT (0.57) models dropped significantly due to limiting the habitat close to samples. Therefore, MAXENT model was more applicable to predict species’ potential habitat in the complex forest; whereas SVM and DT models would tend to underestimate the potential habitat of LLCs.
The purpose of this study is twofold, one is to establish species distribution model (SDM) of Brainea insignis (cycad fern, CF) based on the data measured by different GNSS receivers (survey-grade and recreational utility), so as to explore the impact of positioning quality on the model. Another one is to overcome the problem with insufficient samples for deep learning algorithm used to establish SDM. The results showed that even a few meters of error can cause the model to degrade, with the kappa value dropping by a maximum of 20.9%. Therefore, researchers cannot ignore the precision of species location intelligence. The way of extracting training samples has proved to be feasible to deep learning algorithm, in which one first establishes a high-potential habitat map by machine learning methods and then clips training areas input to this algorithm. Through this process, the model accuracy of U-net can reach above 90%. This opens up new possibilities for species distribution modeling.
Abstract Abstract The forests of Taiwan fir ( Abies kawakamii ) in the Hohuan Mountain area exhibit a two-phase mosaic, fir patches alternating with gaps. The study attempted to apply topographic variables to examine the association between topography and patch-gap pattern in this area. Topographic data layers for GIS analyses were derived from aerial photography. A topographic sheltering index, serving as a surrogate for wind, was developed according to the concepts of shelterbelt and point-in-polygon operation in GIS. Chi-square tests were performed to identify variables significantly associated with this pattern. Elevation and topographic sheltering were highly associated with this pattern, whereas the reverse held true for slope and aspect. Hence, Taiwan fir preferred a cold and humid environment at elevations above 3000 m; it also preferred sheltered sites to windswept sites. The index proved useful for discriminating this pattern in the landscape. The outcomes dovetailed the wind explanation proposed in previous studies in which wind was considered a primary factor causing this pattern. However, in situ monitoring of wind will be needed to verify the importance of wind to this pattern. The index reduced the area of future fieldwork, thereby making it more feasible. The outcomes will provide a valuable basis for modelling the potential habitat of Taiwan fir and a guideline for planning feasible fieldwork so that the model can be verified.
Abstract. With an increase in the rate of species extinction, we should choose right methods that are sustainable on the basis of appropriate science and human needs to conserve ecosystems and rare species. Species distribution modeling (SDM) uses 3S technology and statistics and becomes increasingly important in ecology. Brainea insignis (cycad-fern, CF) has been categorized a rare, endangered plant species, and thus was chosen as a target for the study. Five sampling schemes were created with different combinations of CF samples collected from three sites in Huisun forest station and one site, 10 km farther north from Huisun. Four models, MAXENT, GARP, generalized linear models (GLM), and discriminant analysis (DA), were developed based on topographic variables, and were evaluated by five sampling schemes. The accuracy of MAXENT was the highest, followed by GLM and GARP, and DA was the lowest. More importantly, they can identify the potential habitat less than 10% of the study area in the first round of SDM, thereby prioritizing either the field-survey area where microclimatic, edaphic or biotic data can be collected for refining predictions of potential habitat in the later rounds of SDM or search areas for new population discovery. However, it was shown unlikely to extend spatial patterns of CFs from one area to another with a big separation or to a larger area by predictive models merely based on topographic variables. Follow-up studies will attempt to incorporate proxy indicators that can be extracted from hyperspectral images or LIDAR DEM and substitute for direct parameters to make predictive models applicable on a broader scale.
As climate change getting severer, finding an effective way to establish specie distribution model (SDM) becomes vital, and collecting terrain-related variable is efficient. Chamaecyparis formosensis (Taiwan red cypress, TRC) grow around ridges above 1,800m covered with dry soil or gravel. Abies kawakamii (Taiwan fir, TF) grow near ridges and peaks over 3,000m with impermeable "terrain-shelterbelt" that block away overwhelming moisture. We used digital elevation models (DEM) with four different grid sizes (1, 5, 20, and 40m) to derive variables. We used several types of machine learning algorithms to model SDMs. The most accurate algorithms are decision tree and random forest, and the most suitable resolution is 5m. Elevation and topographic sheltering index are necessary for developing SDMs, and models can be more precise and accurate with using multiple layers of TSIs. As for different species, TRC tends to be majorly influenced by main high ridgeline, and TF is mostly affected by micro terrain.
'/%3e%3cuse xlink:href='%23a' transform='rotate(60)'/%3e%3ccircle r='17' fill='%23000095'/%3e%3ccircle r='15' fill='%23fff'/%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)