As tourism development and human disturbance increase, they have been affecting the functional structure distribution, sustainable utilization of resources, and ecological benefits of nature ...reserves. At the same time, ecological risk has increased significantly. This study proposes ecotourism development patterns for risk areas at each level, to provide a basis for stabilizing and promoting the ecological sustainable development of nature reserves. Yaoluoping National Nature Reserve in China is used as a study case. Based on GaoFen-2 satellite data within the reserve area in 2017, ENVI, Fragstats and ArcGIS10.2 are used for land use classification as well as evaluation indicators selection and analysis. The ecotourism risk assessment model of the reserve is constructed, which is also imbedded with analytic hierarchy process and Ecological Risk Index. The model consists of landscape ecology, topographic hydrology, land use and human activities factors, and it can produce the distribution map at the ecotourism risk level of the reserve. Results show that the high ecotourism risk areas in the reserve are mainly located around rivers and roads, and they are distributed in strips. Overall, the ecotourism risk level in the northern part of the reserve is higher than that in the southern part. Nearly 90% of the regional ecotourism risk is at the middle or low level, implying the reserve in a healthy level overall. However, except for low-risk areas, the proportion of risk areas at all levels in the core zone is higher than that in the buffer zone.
As an important forest type, deciduous broad-leaved forest is crucial for estimating forest carbon sequestration capacity and evaluating forest carbon balance. This study focuses on the natural ...deciduous broad-leaved forest of Mazongling Nature Reserve in Jinzhai County of China. WorldView-2 images were selected as data source. 36 candidate factors including vegetation indices, texture features, and topographic factors were used for modelling. Three machine learning algorithms (i.e., random forest, k-nearest neighbor, and artificial neural network) were used to establish the optimal quantitative retrieval model for natural deciduous broad-leaved biomass. Results showed that the ANN model was the best predictor with R
2
= 0.69 and RMSE = 31.53 (Mg·ha
−1
). Combining the ANN model with the complete spatial coverage of remote sensing data, we developed a distribution map of natural deciduous broad-leaved biomass in the Mazongling forest farm. The estimated average biomass of the study area was 90.34 ± 47.96 Mg·ha
−1
. In addition, the influence of light saturation on model accuracy is also discussed. This study confirms that remote sensing data in temporal and spatial space can improve the model estimation accuracy.
Forest is the largest vegetation carbon pool in the global terrestrial ecosystem. The spatial distribution and change of forest biomass are of importance to reveal the surface spatial variation and ...driving factors, to analyze and evaluate forest productivity, and to evaluate ecological function of forest. In this study, broad-leaved forests located in a typical state nature reserve in northern subtropics were selected as the study area. Based on ground survey data and high-resolution remote sensing images, three machine learning models were used to identify the best remote sensing quantitative inversion model of forest biomass. The biomass of broad-leaved forest with 30-m resolution in the study area from 1998 to 2016 was estimated by using the best model about every two years. With the estimated biomass, multiple leading factors to cause biomass temporal change were then identified from dozens of remote sensing factors by investigating their nonlinear correlations. Our results showed that the artificial neural network (ANN) model was the best (R2 = 0.8742) among the three, and its accuracy was also much higher than that of the traditional linear or nonlinear models. The mean biomass of the broad-leaved forest in the study area from 1998 to 2016 ranged from 90 to 145 Mg ha−1, showing an obvious temporal variation. Instead of biomass, biomass change (BC) was studied further in this research. Significant correlations were found between BC in broad-leaved forest and three climate factors, including average daily maximum surface temperature, maximum precipitation, and maximum mean temperature. It was also found that BC has a strong correlation with the biomass at the previous time (i.e., two years ago). Those quantitative correlations were used to construct a linear model of BC with high accuracy (R2 = 0.8873), providing a new way to estimate the biomass change of two years later based on the observations of current biomass and the three climate factors.
The interference of background noise leads to the extremely high spatial complexity of hyperspectral data. Sensitive band selecting is an important task to minimize or eliminate the influence of ...non-target elements. In this study, Taylor expansion is innovatively used to identify core wavelengths/bands of hyperspectral data. Unlike other traditional methods, this proposed Taylor-CC method considers more local and global information of spectral function to estimate the linear/nonlinear correlation between two wavelengths. Using samples of hyperspectral data with a wavelength range of 350–2500 nm and SPAD for Camellia oleifera, this Taylor-CC method is compared with the traditional PCC method derived from the Pearson correlation coefficient. Using the 240 samples with their different 57 core wavelengths identified by the Taylor-CC method and PCC method, three machine models (i.e., random forest-RF, linear regression-LR, and artificial neural network-ANN) are trained to compare their performances. Their results show that the correlation matrix from the Taylor-CC method represents a clear diagonal pattern with near zero values at most locations away from the diagonal, and all three models confirm that the Taylor-CC method is superior to the PCC method. Moreover, the SPAD spectral response relationship based on machine learning algorithms is constructed, and ANN is the best prediction performance among the three models when using the core wavelengths identified by the Taylor-CC method. The Taylor-CC method proposed in this study not only lays a mathematical foundation for the next analysis of the response mechanism between spectral characteristics and nutrient content of Camellia leaf, but also provides a new idea for the correlation analysis of adjacent spectral bands for hyperspectral signals in many applications.
The rapid development of large-scale deep neural networks has put forward an urgent demand for the efficiency of parallel training. Recently, bidirectional pipeline parallelism has been recognized as ...an effective approach for improving training throughput. This paper proposes MixPipe, a novel bidirectional pipeline parallelism for efficiently training large-scale models in synchronous scenarios. Compared with previous proposals, MixPipe achieves a better balance between pipeline utilization and device utilization, which benefits from the flexible regulating for the number of micro-batches injected into the bidirectional pipelines at the beginning. MixPipe also features a mixed schedule to balance memory usage and further reduce the bubble ratio. Evaluation results show that: for Transformer based language models (i.e., Bert and GPT-2 models), MixPipe improves the training throughput by up to 2.39× over the state-of-the-art synchronous pipeline approaches.
Chlorophyll is a crucial physiological and biochemical indicator that impacts plant photosynthesis, accumulation of photosynthetic products, and final yield. The measurement and analysis of ...chlorophyll content in plants can provide valuable insights into their nutritional status and overall health. The non-destructive and efficient estimation of relevant plant physiological and biochemical indicators using hyperspectral technology can provide a reliable method for collecting data on nutrient levels and health status during plant growth and development. Fifty-three
Carya illinoensis
plants of Jiande and Changlin series known for their exceptional qualities and significant economic benefits were used as the research object for collecting their leaf and canopy hyperspectral data. Firstly, fractional order derivative (FOD) was used for spectral preprocessing. Secondly, the spectral response relationship between spectrum and relative chlorophyll content (soil and plant analyzer development, SPAD) was explored by combining single-band and two-band spectral index (normalized difference spectral index, NDSI). The correlation coefficient of Pearson correlation analysis was used to estimate the linear correlation between variables. Finally, the correlation between the spectral feature variables and SPAD was analyzed and calculated. Top 10 absolute values of the correlation coefficients were screened out as modeling variables. eXtreme gradient boosting (XGBoost) machine learning algorithm was used to construct the optimal estimation model of SPAD of
Carya illinoensis
leaves. Results showed that the correlation between leaf and canopy spectrum after FOD pretreatment and SPAD was substantially improved, compared with raw spectrum. FOD combined with leaf and canopy NDSI was more effective than single band in improving the correlation between spectral characteristics and target components, which was increased by 0.166 and 0.338, respectively. The leaf spectrum could estimate SPAD more accurately than that of canopy spectrum. The optimal SPAD model was the 0.5th-order derivative transformation combined with two-band leaf spectral index (NDSI) model. The
R
2 P was 0.788, and the RMSEP was 0.842 in prediction set. On one hand, this study confirms the feasibility of rapid and non-destructive estimation of SPAD of
Carya illinoensis
leaves using hyperspectral technology. On the other hand, FOD combined with two-band spectral indices can significantly improve the response relationship between spectral characteristics and target variables, enrich hyperspectral data processing methods, and propose a novel approach for the detection of plant nutrient level and health.
The topographical advantage is the contribution of topographic and traffic conditions to the operational efficiency such as afforestation, cutting, logging, and transportation of forestland. The ...classification of topographical advantage is of great importance to evaluate the costs of afforestation and cutting. In this paper, slope, distance, and elevation were selected as three main factors influencing the topographical advantage of forestland according to the Expert Scoring method. The Analytic Hierarchy Process was used to determine the weight of each factor, and ArcGIS10.2 software was used for spatial analysis of terrain and traffic data. The topographical advantage was then divided by the equal-difference method. We applied this method to Lingnan forest farm in Xiuning County, China. Results showed that it was difficult for afforestation and cutting in Lingnan forest farm. This paper presents a quantitative method combining spatial analysis and the Analytic Hierarchy Process for the topographical advantage, which will provide a scientific basis for the cost-effective accounting of afforestation.
Nowadays, there are lots of disks from various disk models in datacenter. It is a challenge to make failure prediction for all disk models with high precision and high coverage. One-for-one modeling, ...transfer learning modeling and one-for-all modeling are proposed to address the challenge. However, none of them works well for all disk models and the automation problem for method selection and parameter tuning still persists. In this paper, we propose OME, an optimized modeling engine for disk failure prediction in heterogeneous datacenter. It builds a basis predictive model with one-for-all modeling and searches for the optimized with one-for-one and transfer learning modeling for every disk model. To achieve automation, OME employs a simple but effective transfer learning method, does cross-validation for comparison, prunes the tuning space, and constructs a directed acyclic graph for parallelism. Evaluation on a dataset from a real-world datacenter shows that OME outperforms a one-for-all predictive model from previous work by 18.5% overall, and the improvement for 43.3% disk models reaches over 30%.
Recently, a large number of DNN inference services have emerged in public clouds, making the low-cost deployment of DNN inference services a hot research topic. Previous studies have failed to take ...into account GPU heterogeneity and batch processing, both of which will seriously affect the financial cost as well as the latency. In this paper, we study the problem of DNN inference service deployment in public cloud, considering both GPU heterogeneity and batch processing. The goal is to minimize the financial costs under the constraint of latency. We propose Jily, an autoscaling scheduler for DNN inference services to minimize the cost while satisfying the given latency SLO. Jily finds the optimal heterogeneous GPU instance provisioning through a DNN inference model profiler, a latency estimator, a workload predictor and a cost-aware scaler. Simulation results demonstrate that Jily can reduce average cost by up to 28% compared to a state-of-the-art autoscaling approach. Further, Jily has been proved to have good versatility and robustness under different batching mechanisms and latency SLO constrains.
► The first meet-in-the-middle attack against block cipher ARIA is presented. ► Some new 3-round and 4-round distinguishing properties of ARIA are found. ► We can attack 6-round ARIA-128, 7-round ...ARIA-192 and 8-round ARIA-256. ► This is the first attack on 8-round ARIA-256.
In this paper, the meet-in-the-middle attack against block cipher ARIA is presented for the first time. Some new 3-round and 4-round distinguishing properties of ARIA are found. Based on the 3-round distinguishing property, we can apply the meet-in-the-middle attack with up to 6 rounds for all versions of ARIA. Based on the 4-round distinguishing property, we can mount a successful attack on 8-round ARIA-256 for the first time. Furthermore, the 4-round distinguishing property could be improved which leads to a 7-round attack on ARIA-192. Compared with the existing cryptanalytic results on ARIA, the meet-in-the-middle attack has a huge precomputation and memory complexities. However, we can do the precomputation once and for all. These results show that 8-round ARIA-256 is not immune to the meet-in-the-middle attack.