Co-designed Practical Use of Probabilistic Climate Advisories among Smallholder Farmers: A Balance between Confidence and Caution

Especially for smallholder farmers with limited land and financial resources,farming in arid and semi-arid lands(ASALs),where season-to-season rainfall fluctuation dictates production,is a risky business.Through participatory approaches,this study compares deterministic and probabilistic interpretations of climate forecasts and their use by smallholder farmers through a crop-growing season.The study revealed that deterministic advisories are good for smallholder farmers only when formulated from forecasts with higher accuracy than the historical climatological distribution.Otherwise,they cause farm loss in terms of labor and inputs.On the other hand,probabilistic advisories help farmers spread the risk to cater to all the uncertainty and in so doing bring out a balance between confidence and caution.However,farmers must be supported with enough sensitization to comprehend forecast probability,translate it into probabilistic advisories and use that to plan and manage farm activities.The findings support the hypothesis providing packaged climate products in transparent probabilistic terms in place of deterministic form can overcome inherent credibility challenges.The study’s conclusion highlights important takeaways and new understandings of the advantage of using probabilistic advisories among resource-poor smallholder farmers.

A New Method for Diagnosis of Leukemia Utilizing a Hybrid DL-ML Approach for Binary and Multi-Class Classification on a Limited-Sized Database

Infection of leukemia in humans causes many complications in its later stages.It impairs bone marrow’s ability to produce blood.Morphological diagnosis of human blood cells is a well-known and well-proven technique for diagnosis in this case.The binary classification is employed to distinguish between normal and leukemiainfected cells.In addition,various subtypes of leukemia require different treatments.These sub-classes must also be detected to obtain an accurate diagnosis of the type of leukemia.This entails using multi-class classification to determine the leukemia subtype.This is usually done using a microscopic examination of these blood cells.Due to the requirement of a trained pathologist,the decision process is critical,which leads to the development of an automated software framework for diagnosis.Researchers utilized state-of-the-art machine learning approaches,such as Support Vector Machine(SVM),Random Forest(RF),Na飗e Bayes,K-Nearest Neighbor(KNN),and others,to provide limited accuracies of classification.More advanced deep-learning methods are also utilized.Due to constrained dataset sizes,these approaches result in over-fitting,reducing their outstanding performances.This study introduces a deep learning-machine learning combined approach for leukemia diagnosis.It uses deep transfer learning frameworks to extract and classify features using state-of-the-artmachine learning classifiers.The transfer learning frameworks such as VGGNet,Xception,InceptionResV2,Densenet,and ResNet are employed as feature extractors.The extracted features are given to RF and XGBoost classifiers for the binary and multi-class classification of leukemia cells.For the experimentation,a very popular ALL-IDB dataset is used,approaching a maximum accuracy of 100%.A private real images dataset with three subclasses of leukemia images,including Acute Myloid Leukemia(AML),Chronic Lymphocytic Leukemia(CLL),and Chronic Myloid Leukemia(CML),is also employed to generalize the system.This dataset achieves an impressive multi-class classification accuracy of 97.08%.The proposed approach is robust and generalized by a standardized dataset and the real image dataset with a limited sample size(520 images).Hence,this method can be explored further for leukemia diagnosis having a limited number of dataset samples.

Indicator Approach to Assessing Climate Change Vulnerability of Communities in Kenya: A Case Study of Kitui County

Community vulnerability to climate change can be conceptualized as an aggregate of three vulnerability components: exposure to climatic stress, sensitivity to climate stress and adaptive capacity. However, even within similar regions these vulnerability components are spatially differentiated necessitating the understanding of a regions vulnerability pattern before targeting adaptation assistance. This research sought to understand the differentiated vulnerability patterns of communities in Kitui County as well as the existing coping strategies to guide implementation of adaptation assistance. Indicator approach to vulnerability assessment and focus group discussions were used to understand the vulnerability pattern and coping strategies respectively. Results showed a differentiated vulnerability pattern with a west to east gradient across Kitui County. The pattern exhibited less vulnerability scores on the western and central parts and more vulnerability scores on the eastern and northern parts of the County. Existing coping strategies have become inadequate with increasing climate variability, severity and frequency of extreme climate events, which render the communities even more vulnerable. The patterns of vulnerability can guide appropriate targeting of adaptation assistance and in turn lead to improved climate change resilience and community livelihoods.

Climate Change Projections and the Associated Potential Impacts for Somalia

Somalia has faced severe challenges linked to climate variability, which has been exacerbated by conflict and limited governance that persisted for decades. Today climate extremes such as floods, drought, and coastal marine severe systems among others are always associated with the destruction of property and livelihoods;losses of lives lost, migrations, and resource based conflicts among many other miseries. Intergovernmental Panel on Climate Change (IPCC) has shown that climate change is real and requires sound knowledge of local future climate change scenarios. The study attempted to provide projected rainfall and temperature change scenarios over Lower Jubba, Somalia. This was done using the downscaled Coordinated Regional Downscaling Experiment (CORDEX) RCMs data. The simulated temperature and rainfall data derived from the CORDEX RCMs ensemble were compared with the observed data. The study focused on the IPCC projected periods of 2030, 2050 and 2070 benchmarks. Analysis of the projected rainfall indicated a decreasing trend in rainfall leading up to 2030 followed by an increase in rainfall with the 2050 and 2070 scenarios. In the case of temperature, the projections from all the models showed increase in minimum and maximum temperatures in all seasons and sub periods, like being observed by temperature projection over other parts of the world. The 2030, 2050 and 2070 projected rainfall and temperature change scenarios show that Somalia future development and livelihoods will in future face increased threats of climate extremes unless effective climate smart adaptation systems form integral components of national development strategies.

Combined QTL mapping,GWAS and transcriptomic analysis revealed a candidate gene associated with the timing of spring bud flush in tea plant(Camellia sinensis)

Dear Editor,The timing of the spring bud f lush(TBF)is a crucial agro-nomic trait for the tea plant,as it strongly influences the yield and economic value of harvested fresh tea leaves.The TBF of tea plant is generally defined as the date when>30%of the growing tender shoots have reached the stage of one bud with one to three leaves,referred as to the stage of one and a bud,two and a bud,and three and a bud,respectively.

Projection of Future Changes in Elephant Population in Amboseli under Representative Concentration Pathways

Within savanna environments, movements of elephant are influenced by changes in climate especially seasonal rainfall. In this study, we investigated the possible changes in elephant population based on projected rainfall changes using regional climate models (RCM) and Representative Concentration Pathways (RCPs). The relationship between elephant and rainfall was modelled against annual, wet season, dry season rainfall based on various time lags. Future relation between elephant and rainfall was projected based on three RCPs;2.6, 4.5 and 8.5. There was a strong linear relationship between elephant and October-November-December (OND) rains with time lag of 13 years (Y = −4016.43 + 19.11x, r2 = 0.459, P = 0.006). The rainfall trends for RCP 2.6 and 4.5 showed a slight increase in annual rainfall for the period 2006-2100 but driven by OND increases. Rainfall increase for RCP 8.5 was significant and was driven by increase in both March-April-May (MAM) and OND. These rainfall dynamics had influence on the projected elephant population in the Amboseli ecosystem. For RCP 2.6 and 4.5 the elephant population increase was 2455 and 2814 respectively. RCP 8.5 elephant population doubled to an average of 3348 elephants. In all the RCPs there are seasonal and yearly variations and absolute number varies from the average. The range of variation is small in RCPs 2.6 and 4.5 compared to RCP 8.5. Evidently, elephant population will increase based on projected rainfall projections surpassing park capacity. It therefore, requires that the Park authority put in place measures that could contain these numbers including opening of blocked wildlife corridors, maintain the cross border movement of Amboseli elephant with Tanzania in that case ensure there is no poaching. Lastly, work with local communities so that they can benefit from tourism through setting up conservancies through which they could minimize the human elephant conflicts based on the projected elephant population.

Iris Liveness Detection Using Fragmental Energy of Haar Transformed Iris Images Using Ensemble of Machine Learning Classifiers

Contactless verification is possible with iris biometric identification,which helps prevent infections like COVID-19 from spreading.Biometric systems have grown unsteady and dangerous as a result of spoofing assaults employing contact lenses,replayed the video,and print attacks.The work demonstrates an iris liveness detection approach by utilizing fragmental coefficients of Haar transformed Iris images as signatures to prevent spoofing attacks for the very first time in the identification of iris liveness.Seven assorted feature creation ways are studied in the presented solutions,and these created features are explored for the training of eight distinct machine learning classifiers and ensembles.The predicted iris liveness identification variants are evaluated using recall,F-measure,precision,accuracy,APCER,BPCER,and ACER.Three standard datasets were used in the investigation.The main contribution of our study is achieving a good accuracy of 99.18%with a smaller feature vector.The fragmental coefficients of Haar transformed iris image of size 8∗8 utilizing random forest algorithm showed superior iris liveness detection with reduced featured vector size(64 features).Random forest gave 99.18%accuracy.Additionally,conduct an extensive experiment on cross datasets for detailed analysis.The results of our experiments showthat the iris biometric template is decreased in size tomake the proposed framework suitable for algorithmic verification in real-time environments and settings.

Challenges and Limitations in Speech Recognition Technology:A Critical Review of Speech Signal Processing Algorithms,Tools and Systems

Speech recognition systems have become a unique human-computer interaction(HCI)family.Speech is one of the most naturally developed human abilities;speech signal processing opens up a transparent and hand-free computation experience.This paper aims to present a retrospective yet modern approach to the world of speech recognition systems.The development journey of ASR(Automatic Speech Recognition)has seen quite a few milestones and breakthrough technologies that have been highlighted in this paper.A step-by-step rundown of the fundamental stages in developing speech recognition systems has been presented,along with a brief discussion of various modern-day developments and applications in this domain.This review paper aims to summarize and provide a beginning point for those starting in the vast field of speech signal processing.Since speech recognition has a vast potential in various industries like telecommunication,emotion recognition,healthcare,etc.,this review would be helpful to researchers who aim at exploring more applications that society can quickly adopt in future years of evolution.

Synthesis and optimization of high surface area mesoporous date palm fiber-based nanostructured powder activated carbon for aluminum removal

Date palm fiber(DPF)derived from agrowaste was utilized as a new precursor for the optimized synthesis of a costeffective,nanostructured,powderactivated carbon(nPAC)for aluminum(Al3+)removal from aqueous solutions using carbonization,KOH activation,response surface methodology(RSM)and central composite design(CCD).The optimum synthesis condition,activation temperature,time and impregnation ratio were found to be 650℃,1.09 hour and 1:1,respectively.Furthermore,the optimum conditions for removal were 99.5%and 9.958 mgg 1 in regard to uptake capacity.The optimum conditions of nPAC was analyzed and characterized using XRD,FTIR,FESEM,BET,TGA and Zeta potential.Moreover,the adsorption of the Al3+conditions was optimized with an integrated RSMCCD experimental design.Regression results revealed that the adsorption kinetics data was well fitted by the pseudosecond order model,whereas the adsorption isotherm data was best represented by the Freundlich isotherm model.Optimum activated carbon indicated that DPF can serve as a costeffective precursor adsorbent for Al^(3+)removal.

Key global climate governance problems and Chinese countermeasures

Presently,the full implementation of the negotiations and collaborations under the Paris Agreement faces new key problems and severe challenges.These problems and challenges include the following:how to honor the principle of“common but differentiated responsibilities”to facilitate a comprehensive,balanced,and effective implementation of the key elements of the Paris Agreement,such as adaptation,mitigation,finance,technology,capacity building,and transparency;how to uphold and maintain the status of China and other emerging countries as developing countries in light of the requirements of the United Nations Framework Convention on Climate Change and the historical responsibilities of these countries;and how to assess the goal of limiting the global temperature increase to 1.5℃and what constitutes an equitable carbon mitigation pathway for different types of countries.Developed countries and developing countries have drastically diverging views on carbon border adjustment measures for trade with developing countries proposed by several developed countries such as the European Union.Developed countries have demonstrated obvious intentions and actions designed to weaken and neglect the principle of“common but differentiated responsibilities”,to impose mitigation pressure on developing countries,to shift the responsibilities for emissions onto others,and to pass on the costs of mitigation.The maneuvering among different types of countries and interest groups has become increasingly intense.In response,China must maintain its strategic focus,adhere to the goals and principles established by the Paris Agreement,stick to its strategic positioning as a developing country,solidify strategic support from the developing world,and safeguard the legitimate rights and interests of developing countries.China played a conducive role in facilitating the Paris Agreement and has become an active participant,contributor,and leader in global climate governance.China must continue to follow Xi Jinping Thought on Socialism with Chinese Characteristics for a New Era and its conception of ecological civilization and the concept of building a community of common destiny,to actively lead the cooperation process in the construction of a global climate governance system characterized by equity,justice,and win-win collaborations,and to promote compliance with the Paris Agreement.At the same time,China should accelerate the green,low-carbon,circular transformation of its economy;accelerate the coordinated governance of the economy,environment,and climate change;and formulate and implement a long-term low-carbon development strategy.By the middle of the 21st century,while achieving the goal of building a great modern socialist country,China can also achieve a deep decarbonization development path that is in line with the goal of limiting the global temperature increase to well below 2°C and pursuing efforts to limit the increase to 1.5℃.

Debris flow simulation 2D(DFS 2D):Numerical modelling of debris flows and calibration of friction parameters

Debris flows are rapid mass movements with a mixture of rock,soil and water.High-intensity rainfall events have triggered multiple debris flows around the globe,making it an important concern from the disaster management perspective.This study presents a numerical model called debris flow simulation 2D(DFS 2D)and applicability of the proposed model is investigated through the values of the model parameters used for the reproduction of an occurred debris flow at Yindongzi gully in China on 13 August 2010.The model can be used to simulate debris flows using three different rheologies and has a userfriendly interface for providing the inputs.Using DFS 2D,flow parameters can be estimated with respect to space and time.The values of the flow resistance parameters of model,dry-Coulomb and turbulent friction,were calibrated through the back analysis and the values obtained are 0.1 and 1000 m/s^(2),respectively.Two new methods of calibration are proposed in this study,considering the crosssectional area of flow and topographical changes induced by the debris flow.The proposed methods of calibration provide an effective solution to the cumulative errors induced by coarse-resolution digital elevation models(DEMs)in numerical modelling of debris flows.The statistical indices such as Willmott's index of agreement,mean-absolute-error,and normalized-root-mean-square-error of the calibrated model are 0.5,1.02 and 1.44,respectively.The comparison between simulated and observed values of topographic changes indicates that DFS 2D provides satisfactory results and can be used for dynamic modelling of debris flows.

Low Profile UHF Antenna Design for Low Earth-Observation CubeSats

This paper reveals a new design of UHF CubeSat antenna based on a modified Planar Inverted F Antenna(PIFA)for CubeSat communication.The design utilizes a CubeSat face as the ground plane.There is a gap of 5 mm beneath the radiating element that facilitates the design providing with space for solar panels.The prototype is fabricated using Aluminum metal sheet and measured.The antenna achieved resonance at 419 MHz.Response of the antenna has been investigated after placing a solar panel.Lossy properties of solar panels made the resonance shift about 20 MHz.This design addresses the frequency shifting issue after placing the antenna with the CubeSat body.This phenomenon has been analyzed considering a typical 1U and 2U CubeSat body with the antenna.The antenna achieved a positive realized gain of 0.7 dB and approximately 78%of efficiency at the resonant frequency with providing 85%of open space for solar irradiance onto the solar panel.

Land Cover Changes in Lower Jubba Somalia

Charcoal is the main cooking source of energy used by millions of households in Somalia and has been described as “black gold” because of the revenue it produces. The objective of this study was to understand the extent of land cover change, given the widely reported charcoal trade in the South of Somalia. Land cover change analysis was done using remotely data from Landsat imagery. Different images covering all districts in Lower Jubba from 1993/95, 2000 and 2014 were analysed and compared. A survey was conducted in Lower Jubba to determine the divers of deforestation and degradation in the region. Results showed a 50% reduction in forest cover and a 17% reduction in woodlands between 1993/95 and 2014. Results from the survey showed charcoal production as a maladaptive response to climate extremes. If business continues as usual with deforestation, the entire area could completely be deforested in the future. Results from this study can be useful in the development of strategies for reforestation, environmental management and sustainable development for this region.

Evaluation of antidepressant activity of methanolic and hydroalcoholic extracts of Acorus calamus L.rhizome through tail suspension test and forced swimming test of mice

Objective:Acorus calamus(AC)L.(Araceae)is an annual semi-aquatic and aromatic plant found in Europe,North America and Asia.Its rhizomes are often used by Native Americans,Americans,and Chinese as well as by other cultures.Ethnobotanical studies and documents have shown their use in various disease treatments,such as insomnia,mental disorders,diabetes mellitus,epilepsy,inflammation,asthma,neuropathic pain,and diarrhea.In this study,the antidepressant activity of methanolic and hydroalcoholic extracts of the AC rhizome part in mice was investigated.Methods:Three doses of methanolic extract of AC rhizome(MEACR)(25,50 and 100 mg/kg b.wt),three doses of hydroalcoholic extract of AC rhizome(HAACR)(100,200 and 400 mg/kg b.wt),and standards(imipramine,15 mg/kg b.wt and fluoxetine,20 mg/kg b.wt)was daily oral administration to the mice for consecutive 14 days.The extract effect on the immobility time was monitored by a tail suspension test(TST)and a forced swimming test(FST).Monoamine oxidase(MAO)levels were also analyzed using standard methods.Results:The optimum antidepressant activity was viewed at 100 mg/kg b.wt of MEACR extract and400 mg/kg b.wt of HAACR extract with 23.82%and 20.59%immobility period reduction,respectively.Besides,the extracts weakened the FST-induced elevation of MAO activity significantly and returned to near-normal levels of neurotransmitters in the brain.100 mg/kg b.wt or above of MEACR extract significantly prevented the MAO-A and MAO-B activities in mice brain at a dose-dependent fashion.But,just 400 mg/kg b.wt of HAACR extract prevented the activity of MAO-A and MAO-B.Fluoxetine and imipramine showed a tendency to prevent the activity of MAO-A and MAO-B.Conclusion:This study suggests that AC rhizome extract mediated antidepressant activity by modulating the central neurochemical and hypothalamic-pituitary-adrenal(HPA)axis in response to FST and TSTinduced stress.Therefore,AC rhizome extract can be used as a valuable plant supplement to treat depressive disorders.

Characteristics of non-volatile metabolites in fresh shoots from tea plant(Camellia sinensis)and its closely related species and varieties

Tea plant(Camellia sinensis)and its closely related species and varieties belong to Sect.Thea(L.)Dyer,Camellia L.There are abundant compounds in the fresh shoots of section Thea(L.)Dyer species and varieties.Their variation in different tea species and varieties is unclear.Fresh shoots from 336 accessions of C.sinensis and its closely related species and varieties were harvested and their non-volatile metabolites were detected through UPLC-MS(ultra-performance liquid chromatography-mass spectrometry).A total of 374 non-volatile metabolites were identified,which can be divided into 27 categories.Among them,32 compounds were flavonoid polymers.The tea plants were divided into two groups,according to the Calinski criterion according to the composition of metabolites.The top 30 differential metabolites in C.sinensis var.sinensis,C.sinensis var.assamica,C.sinensis var.pubilimba,C.tachangensis,and C.taliensis,belong to amino acids and their derivatives,benzoic acid derivatives,carbohydrates,coumarins,flavonol glycosides,organic acids,quinoline acid and its derivatives.The results provide new insights for further understanding the characteristic metabolites of tea plant and its closely related species and varieties.

Potential Impacts of Temperature Projections on Selected Large Herbivores in Savanna Ecosystem of Kenya

Due to global land surface warming, severe temperature events are expected to occur more frequently and more extremely causing changes in biodiversity and altering movement and survival of large herbivores. There are increasing observations of escalating wildlife range losses worldwide. In this study, we investigated 15 large wild herbivores (4 migratory, 1 dispersing and 10 residents) and their potential range changes in relation to projected temperatures changes based on three Representative Concentration Pathways (RCPs) 2.6, 4.5 and 8.5. Previous studies of Kenyan savannah have shown that increases in temperature can reduce the densities of wildlife significantly and after certain thresholds the species can be lost in those landscapes. The range maps of the 15 species were developed from aerial censuses that have been conducted in the arid and semi-arid lands of Kenya. We analysed temperature changes for the three RCPs for the periods 2030s, 2050s and 2070s. And based on the temperature threshold for each of the 15 species we analysed which wildlife range areas will be lost. Our results project that for the RCP 2.6, 3 out of the 15 species are projected to lose more than 50% of their range by the year 2030s, and 5 out 15 by 2050s and 4 of 15 by 2070s. The second climate scenario of RCP 4.5 projects that by 2030s, 3 species will lose more than 50% of their range, and in 2050s and 2070s 5 species. The RCP 8.5 which is the extreme scenario of temperature changes projects 5 species to lose their range by 50% in 2030s, 7 species by 2050s and 10 species by 2070s. The extent of range loss was different among species but was severe for buffalo, Thomson’s gazelle, waterbuck, and wildebeest which are also water dependent species. However, the elephant, gerenuk, hartebeest, lesser kudu, and oryx are expected to retain most of their range in all the RCPs scenarios. These range contractions raise serious concerns about the future of wildlife in Kenyan savannah based on projected climate changes. And therefore, it is imperative the wildlife sector develops climate policies and plans that take into account the projected climate scenarios.

Royal Crown Shaped Polarization Insensitive Perfect Metamaterial Absorber for C-, X-, and Ku-Band Applications

This study proposed a new royal crown-shaped polarisation insensitive double negative triple band microwave range electromagnetic metamaterial absorber(MA).The primary purpose of this study is to utilise the exotic characteristics of this perfect metamaterial absorber(PMA)for microwave wireless communications.The fundamental unit cell of the proposed MA consists of two pentagonal-shaped resonators and two inverse C-shaped metallic components surrounded by a split ring resonator(SRR).The bottom thin copper deposit and upper metallic resonator surface are disjoined by an FR-4 dielectric substrate with 1.6 mm thickness.The CST MW studio,a high-frequency electromagnetic simulator has been deployed for numerical simula-tion of the unit cell in the frequency range of 4 to 14 GHz.In the TE mode,the offered MA structure demonstrated three different absorption peaks at 6.85 GHz(C-band),8.87 GHz(X-band),and 12.03 GHz(Ku-band),with 96.82%,99.24%,and 99.43%absorptivity,respectively.The electric field,magnetic field,and surface current distribution were analysed using Maxwell’s-Curl equations,whereas the angle sensitivity was investigated to comprehend the absorption mechanism of the proposed absorber.The numerical results were verified using the Ansys HFSS(high-frequency structure simulator)and ADS(advanced design system)for equivalent circuit models.Moreover,the proposed MA is polarisation and incident angle independent.Hence,the application of this MA can be extended to a great extent,including airborne radar applications,defence,and stealth-coating technology.

全球气候治理新动向与中国应对

After more than 30 years of negotiations,a multilateral climate governance system,with the United Nations Framework Convention on Climate Change(hereinafter referred to as the Convention),the Kyoto Protocol and the Paris Agreement as the key pillars,has been formed worldwide.This system promotes collaboration among all parties to address the challenges of climate change within the framework of sustainable development and to protect the Earth,on which human beings depend.During his speech at the opening ceremony of the Paris Climate Change Conference in 2015,Chinese President Xi Jinping stated,“As an important part of global governance,the global efforts on climate change can be taken as a mirror for us to reflect on what models to have for future global governance and how to build a community of shared future for mankind.Much valuable inspiration may thus be drawn.”1 Climate change is a pressing global crisis and a long-term challenge.It is a global consensus,and a main area for major-power competition to address climate change.In this context,gaining awareness of the latest developments in global climate governance and analyzing the meaningful challenges it presents would hold great practical significance for China’s engagement in global climate governance.

Spatial landslide susceptibility assessment using machine learning techniques assisted by additional data created with generative adversarial networks

In recent years,landslide susceptibility mapping has substantially improved with advances in machine learning.However,there are still challenges remain in landslide mapping due to the availability of limited inventory data.In this paper,a novel method that improves the performance of machine learning techniques is presented.The proposed method creates synthetic inventory data using Generative Adversarial Networks(GANs)for improving the prediction of landslides.In this research,landslide inventory data of 156 landslide locations were identified in Cameron Highlands,Malaysia,taken from previous projects the authors worked on.Elevation,slope,aspect,plan curvature,profile curvature,total curvature,lithology,land use and land cover(LULC),distance to the road,distance to the river,stream power index(SPI),sediment transport index(STI),terrain roughness index(TRI),topographic wetness index(TWI)and vegetation density are geo-environmental factors considered in this study based on suggestions from previous works on Cameron Highlands.To show the capability of GANs in improving landslide prediction models,this study tests the proposed GAN model with benchmark models namely Artificial Neural Network(ANN),Support Vector Machine(SVM),Decision Trees(DT),Random Forest(RF)and Bagging ensemble models with ANN and SVM models.These models were validated using the area under the receiver operating characteristic curve(AUROC).The DT,RF,SVM,ANN and Bagging ensemble could achieve the AUROC values of(0.90,0.94,0.86,0.69 and 0.82)for the training;and the AUROC of(0.76,0.81,0.85,0.72 and 0.75)for the test,subsequently.When using additional samples,the same models achieved the AUROC values of(0.92,0.94,0.88,0.75 and 0.84)for the training and(0.78,0.82,0.82,0.78 and 0.80)for the test,respectively.Using the additional samples improved the test accuracy of all the models except SVM.As a result,in data-scarce environments,this research showed that utilizing GANs to generate supplementary samples is promising because it can improve the predictive capability of common landslide prediction models.

APG: A novel python-based ArcGIS toolbox to generate absence-datasets for geospatial studies

One important step in binary modeling of environmental problems is the generation of absence-datasets that are traditionally generated by random sampling and can undermine the quality of outputs.To solve this problem,this study develops the Absence Point Generation(APG)toolbox which is a Python-based ArcGIS toolbox for automated construction of absence-datasets for geospatial studies.The APG employs a frequency ratio analysis of four commonly used and important driving factors such as altitude,slope degree,topographic wetness index,and distance from rivers,and considers the presence locations buffer and density layers to define the low potential or susceptibility zones where absence-datasets are generated.To test the APG toolbox,we applied two benchmark algorithms of random forest(RF)and boosted regression trees(BRT)in a case study to investigate groundwater potential using three absence datasets i.e.,the APG,random,and selection of absence samples(SAS)toolbox.The BRT-APG and RF-APG had the area under receiver operating curve(AUC)values of 0.947 and 0.942,while BRT and RF had weaker performances with the SAS and Random datasets.This effect resulted in AUC improvements for BRT and RF by 7.2,and 9.7%from the Random dataset,and AUC improvements for BRT and RF by 6.1,and 5.4%from the SAS dataset,respectively.The APG also impacted the importance of the input factors and the pattern of the groundwater potential maps,which proves the importance of absence points in environmental binary issues.The proposed APG toolbox could be easily applied in other environmental hazards such as landslides,floods,and gully erosion,and land subsidence.