Expansion Of Human Settlements Research Articles

Transitional Infrastructures Extending Access to Safe Water in Informal Settlements: A Cross-Sectional Study in Nairobi, Kenya.

There is a pressing need for transitional water infrastructures in rapidly growing cities where conventional infrastructures lag behind human settlement expansion. In Kenya, sectoral innovations have addressed local socioeconomic challenges, but empirical evidence on their efficacy (combining quantitative indicators of safety and continuity) is lacking. We addressed this gap by comparing different water infrastructures in their ability to provide constant access to safe water in informal settlements in Nairobi, Kenya. We conducted a cross-sectional survey including 1,147 households in two informal settlements. Water infrastructures were categorized based on their distribution system: 1) piped to premises; 2) piped to a neighboring compound; 3) public tap/dispenser; and 4) street vendor. We tested associations between these systems with two outcomes: constant water availability and diarrhea (stratified by age group). We used adjusted odds ratios (AORs) to test associations between distribution systems and the selected outcomes, while accounting for confounders. Obtaining water from public taps/dispensers or street vendors was associated with service continuity (AOR = 1.45, 95% confidence interval [CI]: 1.06-1.99; AOR = 11.16, 95% CI: 2.45-50.82). Piped sources were associated with service disruption, especially when obtained from a neighboring compound (AOR = 0.45, 95% CI: 0.28-0.70). Public taps/dispensers were the only system consistently associated with lower odds of diarrhea, notably in children under the age of 5 years (AOR = 0.47, 95% CI: 0.29-0.79). Hence, in cities with a high prevalence of informal settlements and limited financial resources, public taps and dispensers hold promise as transitional water infrastructures.

Genetic improvement and conservation of goats in tropic

Goats indeed have a significant historical and contemporary importance in human civilization, particularly in the realm of agriculture and food production. Their adaptability and widespread distribution have made them crucial for various societies across the world. Goats have played a central role in the Neolithic agricultural revolution, aiding in the spread of human civilization globally. Their adaptability allowed them to thrive in diverse environments, contributing to the sustenance and expansion of human settlements. Goats are highly adaptable and are found in a wide range of geographical regions. Their presence spans across continents, from tropical to temperate climates, showcasing their ability to thrive in various environmental conditions. There is diversity in the production performance of goats based on the region of the world and the specific breeds. Genetic improvement programs aim to enhance economically important traits such as milk production, growth rates and fiber production, thereby increasing productivity and income for goat farmers. Understanding the genetic parameters such as heritabilities and repeatabilities for various traits is crucial for designing effective breeding programs. These parameters provide insights into the genetic potential of goats for traits like milk production, growth and fiber quality. Heritability estimates for reproductive traits, body weight, daily gain and direct and maternal heritability are important for implementing selective breeding strategies aimed at improving overall productivity and efficiency in goat farming. Genetic improvement programs have been implemented in tropical environments to enhance milk production traits in goats. Genetic improvements have also targeted fiber production in goats, with a focus on traits such as grease fleece weight and average fiber diameter. These efforts aim to enhance the quality and quantity of fiber produced by goats for various commercial purposes. Despite the importance of conserving goat breeds with unique characteristics, planned conservation programs in tropical regions are often neglected. It’s emphasized that preserving indigenous goat breeds in their native habitats is essential for maintaining genetic diversity and ensuring future resilience in goat farming.

Isolates of Acanthamoeba species in the marine environment in the Philippines.

Acanthamoebae spp. are considered the most commonly occurring free-living amoebae (FLA) in the environment. Their high resilience enables them to thrive in different types of environments. Using purposive sampling, 80 surface water samples were collected from identified coastal sites in Mariveles, Bataan, and Lingayen Gulf (40 water samples for each). Nineteen (23.75%) of the 80 water samples yielded positive amoebic growth during the 14-day culture and microscopic examination. The polymerase chain reaction confirmed Acanthamoeba spp. DNA in isolates MB1, A3, A4, A7, C5, and D3 using JDP1 and JDP2 primer sets. Further sequencing revealed that the isolates belonged to Acanthamoeba sp., Acanthamoeba culbertsoni, Acanthamoeba castellani, and Acanthamoeba genotype T4. The sequences were deposited in GenBank and registered under accession numbers PP741651, PP767364, PP741728, PP741729, PP767365, and PP767366, respectively. Potential risk factors such as waste disposal, expansion of human settlements to coastal locations, and soil runoffs in these environments should be controlled to mitigate the proliferation of potentially pathogenic strains of FLAs.

Dynamics of Land Use Land Cover Change and Soil Erosion Rate in Chure Landscape of Sudurpaschim Province

Land use land cover, a dynamic process, has become a central component of current strategies in managing natural resources and monitoring environmental changes. This study adopts an integrated GIS and Remote Sensing approach to assess changes in land use, land cover (LU/LC), and soil erosion rates between 2001 and 2021. Land use maps were generated using supervised classification and the Maximum Likelihood algorithm, while RUSEL factors facilitated soil erosion mapping analysis. The findings underscore a remarkable decrease in 'agricultural land' and 'water,' accompanied by a simultaneous increase in 'settlement area,' 'forest area,' and 'bare land.' Agricultural land witnessed an annual decline of 2.5 percent, while water bodies decreased by 0.65 percent in 2021. Forest areas exhibited a 0.09 percent increment from 2001 to 2021, and settlement areas expanded at a rate of 0.41 percent annually. Notably, agricultural land reduction primarily contributed to the growth of settlement areas. Additionally, soil erosion rates rose from 3.82 (t/ha/year) in 2001 to 4.090 (t/ha/year) in 2021, indicating a correlation between land use change and soil erosion. Factors such as increased settlement, population growth, infrastructure development, riverbank cutting, and erosion were associated with the decline in agricultural land. Effective land use planning in the Churia region is imperative to address these changes. Government intervention and stakeholder cooperation are crucial to curbing forest degradation, unchecked human settlement expansion, and riverbank cutting. Furthermore, the study advocates for the intensified use of GIS and Remote Sensing technologies in monitoring and managing natural resources.

Bird communities across different levels of human settlement: A comparative analysis from two northern Amazonian ecoregions

Urban ecosystems are increasingly dominating landscapes globally, so it is critical to understand the effects of human settlements on biodiversity. Bird communities are effective indicators because they are impacted by the size and expansion of human settlements, exemplified by changes in their habitat use, breeding and foraging behaviours, as well as patterns of richness and abundance. Existing studies on bird community responses to human settlements have mainly focused on single ecoregions and large cities, leaving a gap in comparative research on how differently sized human settlements affect bird communities across various ecoregions. To address this gap, we examine species richness, bird abundances and community composition in human settlements, which exhibit variable sizes, populations, landscape configurations, and overall intensity of settlement in two tropical ecoregions in Guyana, Amazonia: forest and savannah. In each ecoregion we explored how different groupings of urban tolerance in birds responded to human settlements of differing population size and building densities. Overall, we found significant differences in bird communities across the varying levels of human settlement intensity in both ecoregions, with greater differences in bird community composition in the forest ecoregion than the savannah region. In both ecoregions, species richness and abundance were highest at the medium level of settlement of human settlement. Our findings suggest that bird tolerance to human settlements varies based on ecoregion and site-level factors. In the savannah, built features may be benefitting birds from all urban tolerance levels, but they have a negative impact on less urban-tolerant species in the forest ecoregion. Our comparative analysis reveals for the first time that the impact of human settlements on avian communities in northern Amazonia varies among ecoregions, indicating that species evolved to live in a savannah may be more tolerant to human settlements than those more evolved to a forest system.

Mapping deforestation and recovery of tropical montane forests of East Africa

Deforestation poses a major threat to the tropical montane forest ecosystems of East Africa. Montane forests provide key and unique ecological and socio-economic benefits to the local communities and host diverse flora and fauna. There is evidence of ongoing deforestation and forest clearance in these montane forests although estimates diverge among different sources suggesting rates of 0.4%–3% yr−1. Quantifying deforestation rates and forest disturbance is critical to design conservation and sustainable management policies for forest management. This study quantified the rate of deforestation and forest recovery over the last three decades for the Mau Forest Complex and Mount Elgon forests in Kenya and Uganda using Landsat time-series satellite imagery. With the analysis, classification accuracies of 86.2% and 90.5% (kappa 0.81 and 0.88) were achieved for the Mau Forest Complex and the Mt Elgon forests, respectively. 21.9% (88,493 ha) of the 404,660 ha of Mau forest was lost at an annual rate of −0.82% yr−1 over the period between 1986 and 2017. More positively, 18.6% (75,438 ha) of the forest cover that was disturbed during the same period and is currently undergoing recovery. In Mt Elgon forest, 12.5% (27,201 ha) of 217,268 ha of the forest cover was lost to deforestation at an annual rate of −1.03% yr−1 for the period between 1984–2017 and 27.2% (59,047 ha) of the forest cover disturbed is undergoing recovery. The analysis further demonstrated agriculture (both smallholder and commercial) was the main driver of forest cover loss in Mau forest, accounting for 81.5% (70,612 ha) of the deforestation, of which 13.2% was due to large scale and 68.3% was related to the smallholders. For the Mt Elgon forest, agriculture was also the main driver accounting for 63.2% (24,077 ha) of deforestation followed by the expansion of human settlements that contributed to 14.7% (5,597 ha) of forest loss. This study provides accurate and novel estimates of the rate of deforestation for the Mau forest complex and Mt Elgon forest ecosystems. These rates are higher than previously estimated and recent deforestation has been identified, which provides a quantitative basis for forest restoration programs and to design conservation policies.

Levels of Radon in Soils of Dodoma City, Central Tanzania

Purpose: Humans receive radiation doses exceeding fifty percent (50%) of the total dose from natural sources as a result of inhaling radon and thoron gases and their daughters. Radon occurs naturally in soils and can diffuse into indoor environments leading to adverse health effects for inhabitants. In this study, measurement of levels of radon gas in soils was performed with the purpose of categorizing areas and highlighting the likelihood of high levels of radon in indoor environments.
 Design/Methodology/ Approach: The study targeted the environs of Dodoma where the rapid expansion of human settlements is ongoing or anticipated. For easy access and convenience, the study was conducted in areas located along main roads leading to the nearby towns/cities. Sampling was done by inserting the drilling rod to a depth of approximately one meter (1 m) below ground level with the aid of a heavy hammer. The alpha pump was used to suck the soil gas from the ground through a metallic tube (the capillary probe) and pressed it into the ionization chamber of the measuring instrument (AlphaGUARD). Radon concentration was read directly from the instrument’s display.
 Findings: It was found that radon concentrations in soil vary from 18.8 to 233.5 kBq.m-3. Based on the radon risk criterion, surveyed areas range from normal to high radon risk categories.
 Research Limitation/Implication: The study only covered a limited area in Dodoma City, and therefore the results may not be representative of the entire city or even the surrounding regions.
 Practical Implications: This study is useful in categorizing building areas based on radon risk criterion with the purpose of reducing possibilities of radon-related health risks; mainly lung cancer to the population.
 Social Implications: Radon is a proven cause of lung cancer in humans. Therefore, knowledge of radon levels in the study area will help in setting the mitigation measures necessary for public health protection.
 Originality / Value/ Novelty: The study demonstrates an approach for estimating radon levels in soils which is beneficial to current and future researchers, environmentalists and regulators, among others.

Urban-rural disparities of carbon storage dynamics in China's human settlements driven by population and economic growth

China has experienced a rapid expansion of human settlement in both urban and rural areas over the past three decades. Regarding the impacts on carbon storage, previous studies that only focus on certain ecosystems cannot reflect urban-rural disparities, resulting in the carbon storage changes in human settlement remaining unknown. In this study, we aimed to explore China's urban-rural disparities in human settlement expansion and direct impacts on carbon storage by using the big Earth data technology. The results showed that from 1990 to 2018, the total amount of China's human settlement expansion reached 175,703.80 km2, and the inner-city, peri-urban, and rural components accounted for 21.00 %, 20.18 %, and 58.82 %, respectively. Along with the general tendency of impervious surface area (ISA) growth, there was more soil organic carbon (SOC) (1254.33 TgC) being sealed beneath ISA (0–100 cm depth), compared to a huge reduction in vegetation biomass carbon (VBC) (91.44 TgC) during the study period. The results further indicated that the change density of either VBC or SOC presented a slightly rising trend along the urban-rural gradient, due to the increasingly common encroachment on vegetation and soil types with higher carbon content. We also found that socioeconomic drivers had a greater influence in urban areas than rural areas, and the related correlation exhibited a descending trajectory in both urban and rural areas. There is thus an urgent need to preserve lands with abundant carbon storage and contain the waste of land resources in rural areas. All stakeholders should pay more attention to concerted and targeted regulation policies for well-planned and eco-friendly human settlement expansion such as enhancing rural land use efficiency and promoting large-scale afforestation and continuous urban greening, which will be critical not only for guiding sustainable urbanization all over China but also for mitigating climate change for the entire world.

Modelling Impact of Urban Expansion on Ecosystem Services: A Scenario-Based Approach in a Mixed Natural/Urbanised Landscape

The present study aims at predicting future land use/land cover (LULC) and quantifying and mapping the ecosystem services (ESs) of water yield, outdoor recreation opportunity and food production in current (here, 2017) and future landscapes in Northern Iran, using the InVEST, Recreation Opportunity Spectrum (ROS) and yield models. To that end, two LULC scenarios known as business as usual (BAU) and protection-based (PB) plan were applied for 2028, using the Markov Artificial Neural Network and Multi-objective land allocation (MOLA) models. The results show that rapid urbanisation, caused by the expansion of human settlements and industrial areas, has led to a decline in the ESs in the region. Compared to the ESs in 2017, the service of water yield increases as urban expansion increases, whereas food production and recreation services decrease as urban expansion increases, under the BAU scenario. On the other hand, in the PB scenario, relatively better conditions can be observed for all three ESs. Considering that the ecological structures of this region have been severely affected by rapid urban expansion, the results of this research will be useful for maintaining the existing ESs and can greatly affect planning and decision-making regarding future development towards urban sustainability.

Human-environment interaction systems between regional and continental scales in mid-latitude Eurasia during 6000�C3000 years ago

<p>The Late Neolithic and Bronze Ages witnessed the extensive expansion of human settlements, along with the dispersal of crops and livestock originating from West and East Asia. These events profoundly reshaped the human-environment relationship in mid-latitude Eurasia and the underlying trans-Eurasian exchange. While the processes and factors that underpin the interaction between human societies and ever-changing environments have been a heated debate in various regions of Eurasia, there is still a lack of synergistic discussion regarding human-environment interactions at regional and continental scales. To this end, we provide a comprehensive review and synthesis of updated radiocarbon dates and archaeobotanical and zooarchaeological data from sites dated between 6000 and 3000 cal. yr BP in mid-latitude Eurasia, coupled with associated archaeological and palaeoclimatic records. The results reveal the emergence and expansion of a number of regional settlement centers along the prehistoric Silk Roads and Eurasian Steppes during the 6<sup>th</sup>�C4<sup>th</sup> millennium cal. yr BP. The prime drivers include the spread of new technologies, human migration, and climate change. As a result of successful food production and increasing social complexity, many areas have experienced rapid population growth, creating a foundation for subsequent widespread expansion of farming and herding communities across Eurasia. Under this overarching picture, many regional patterns arose due to specific natural and social conditions, weaving into broad spatiotemporal variations across Eurasia. A new conceptual model is proposed to depict this feedback loop of the interaction between human-environment systems at and between regional and continental scales.</p>

Spatio-temporal changes in chimpanzee density and abundance in the Greater Mahale Ecosystem, Tanzania.

Species conservation and management require reliable information about animal distribution and population size. Better management actions within a species' range can be achieved by identifying the location and timing of population changes. In the Greater Mahale Ecosystem (GME), western Tanzania, deforestation due to the expansion of human settlements and agriculture, annual burning, and logging are known threats to wildlife. For one of the most charismatic species, the endangered eastern chimpanzee (Pan troglodytes schweinfurthii), approximately 75% of the individuals are distributed outside national park boundaries, requiring monitoring and protection efforts over a vast landscape of various protection statuses. These efforts are especially challenging when we lack data on trends in density and population size. To predict spatio-temporal chimpanzee density and abundance across the GME, we used density surface modeling, fitting a generalized additive model to a 10-year time-series data set of nest counts based on line-transect surveys. The chimpanzee population declined at an annual rate of 2.41%, including declines of 1.72% in riparian forests (from this point forward, forests), 2.05% in miombo woodlands (from this point forward, woodlands) and 3.45% in nonforests. These population declines were accompanied by ecosystem-wide declines in vegetation types of 1.36% and 0.32% per year for forests and woodlands, respectively; we estimated an annual increase of 1.35% for nonforests. Our model predicted the highest chimpanzee density in forests (0.86 chimpanzees/km2 , 95% confidence intervals (CIs) 0.60-1.23; as of 2020), followed by woodlands (0.19, 95% CI 0.12-0.30) and nonforests (0.18, 95% CI 0.10-1.33). Although forests represent only 6% of the landscape, they support nearly one-quarter of the chimpanzee population (769 chimpanzees, 95% CI 536-1103). Woodlands dominate the landscape (71%) and therefore support more than a half of the chimpanzee population (2294; 95% CI 1420-3707). The remaining quarter of the landscape is represented by nonforests and supports another quarter of the chimpanzee population (750; 95% CI 408-1381). Given the pressures on the remaining suitable habitat in Tanzania, and the need of chimpanzees to access both forest and woodland vegetation to survive, we urge future management actions to increase resources and expand the efforts to protect critical forest and woodland habitat and promote strategies and policies that more effectively prevent irreversible losses. We suggest that regular monitoring programs implement a systematic random design to effectively inform and allocate conservation actions and facilitate interannual comparisons for trend monitoring, measuring conservation success, and guiding adaptive management.

Effect of Linear Infrastructure on Protected Areas: A Study Relating to the Giritale Nature Reserve and Angamedilla National Park, Sri Lanka

Rapid urbanization in the dry zone of Sri Lanka has resulted in considerable losses in its original forest cover. Urban expansion, which typically includes expansion of human settlements and commercial establishments, and the construction of linear infrastructural facilities (roads, railways, and transmission lines) have led to many adverse impacts on natural landscapes. Linear infrastructure would be particularly detrimental when natural habitats are fragmented. Here we report on the changes in green cover along a stretch of the Elahera-Giritale B112 road where reconstruction took place during 2017-2019. The road traverses through the Giritale Nature Reserve block II and Angamedilla National Park, in the North Central Province of Sri Lanka. The study area covered a 3.8 km section of the road, 80% of which runs through the protected areas, and a 1 km buffer on either side of this road. We monitored changes in forest cover over the two decades i.e., from 2000 to 2020, using differences in the Normalized Difference Vegetation Index (NDVI), calculated based on the images in Landsat 5,7 and 8 thematic mapper using the ArcGIS platform. The accuracy of the classified habitats was verified using Google Earth images and ground-truthing. Accordingly, non[1]vegetated areas and four types of vegetated areas were identified. The range of NDVI recorded were non-vegetated (0.14-0.39), grasslands (0.39-0.41), shrublands (0.41-0.48), open forests (0.48-0.54) and dense forests (0.54-0.74). The study revealed that there were considerable losses in the forest cover over the 20 years. The non-vegetated habitats within the buffer zone of 200 m on either side of the road accounted for 8.6% of the total non-vegetated areas in the year 2000 whereas this had increased to 15.4% in the year 2020. Similarly, losses were noted for dense and open forests. Scrublands, grasslands, and built-up areas on the other hand have increased, replacing the forest habitats. The findings highlight the need to monitor forest cover losses arising from such linear infrastructure facilities, particularly when they are within or adjacent to protected habitats, and for remedial measures to be taken to strengthen the protection of these vital ecosystems.
 Keywords: Forest cover, Fragmentation, NDVI, Roads

Fast Urban Land Cover Mapping Exploiting Sentinel-1 and Sentinel-2 Data

The rapid change and expansion of human settlements raise the need for precise remote-sensing monitoring tools. While some Land Cover (LC) maps are publicly available, the knowledge of the up-to-date urban extent for a specific instance in time is often missing. The lack of a relevant urban mask, especially in developing countries, increases the burden on Earth Observation (EO) data users or requires them to rely on time-consuming manual classification. This paper explores fast and effective exploitation of Sentinel-1 (S1) and Sentinel-2 (S2) data for the generation of urban LC, which can be frequently updated. The method is based on an Object-Based Image Analysis (OBIA), where one Multi-Spectral (MS) image is used to define clusters of similar pixels through super-pixel segmentation. A short stack (<2 months) of Synthetic Aperture Radar (SAR) data is then employed to classify the clusters, exploiting the unique characteristics of the radio backscatter from human-made targets. The repeated illumination and acquisition geometry allows defining robust features based on amplitude, coherence, and polarimetry. Data from ascending and descending orbits are combined to overcome distortions and decrease sensitivity to the orientation of structures. Finally, an unsupervised Machine Learning (ML) model is used to separate the signature of urban targets in a mixed environment. The method was validated in two sites in Portugal, with diverse types of LC and complex topography. Comparative analysis was performed with two state-of-the-art high-resolution solutions, which require long sensing periods, indicating significant agreement between the methods (averaged accuracy of around 90%).

Assessment of conservation challenges in and around Gibe Sheleko National Park, southwestern Ethiopia

Most of Ethiopia’s National Parks are affected by anthropogenic factors. The objective of this study was to assess the major wildlife threatening factors of Gibe Sheleko National Park (GSNP) through semi-structured questionnaire, focus groups discussion and observation. The survey was carried out from December, 2018 to August, 2020. A total of 281 randomly selected household heads from eight Kebeles and 15 Park management staff were interviewed. The identified threats include: overgrazing, expansion of human settlement and agricultural practices, fuelwood collection, source of food (bushmeat, fishes and wild honey) collection, invasive vegetation species, human induced fire, human-wildlife conflict and source of house construction materials. The majority (71.17%) of the respondents used the Park as means of grazing land followed by sources of fuelwood (48.26%). Crop raiding is a serious problem in the study area as stated by 84.46% of the respondents. Identified crop raiders include: olive baboon, vervet monkey, warthog, bushpig, porcupine, hippopotamus and antelope species. About 78.14% of the respondents stated that guarding was the most common type of crop raiders’ protection method. The majority (55.26%) of the respondents had positive attitudes towards conservation of the Park. Significant variation was observed in the types of natural resource utilization, types of human-wildlife conflict, trends of crop damage, population status of crop raiders, methods used to protect crop raiders and their attitudes towards GSNP conservation (P < 0.05). In general, GSNP is exposed to multiple conservation challenges. Therefore, for the sustainability of the Park, cooperation among different stakeholders is essential.

Different effects of human settlements changes on landscape fragmentation in China: Evidence from grid cell

Exploring how human settlement expansion affects landscape fragmentation is particularly critical to understanding the complex interactions between human activities and landscape functions, patterns, and processes. Here, we use recently developed built-up data and land use data to characterize this effect and its spatial–temporal heterogeneity between 1975 and 2014 in China based on the grids at the national level. Findings suggest that the mean built-up ratio has enlarged three-fold in the past 40 years. The landscape pattern has become increasingly fragmented. Due to anthropogenic encroachment, human settlement expansion has become directly associated with natural habitat loss. Meanwhile, the swift growth of settlements leads to landscape fragmentation with a snowballing number of patches and reducing mean patch size. However, landscape isolation is negatively correlated with settlement expansion. Contrary to traditional perception, the influence of settlement growth on landscape fragmentation in large cities is not as pronounced as that of small and medium cities. Furthermore, there are significant regional differences and gradient effects in the impact of settlement expansion on landscape fragmentation. Specifically, this impact is most intense in western China, followed by central China, and the weakest in eastern China. Several innovative policy implications of these findings are discussed.

Spatial Expansion of Human Settlement during the Longshan Period (~4.5–~3.9 ka BP) and Its Hydroclimatic Contexts in the Lower Yellow River Floodplain, Eastern China

Obvious spatial expansion of human settlement occurred in the lower Yellow River floodplain during the Longshan period, but the external factors driving this expansion remain unclear. In this study, we first delineated the hydroclimatic changes at both regional and local scales within and around the lower Yellow River floodplain and then examined the relationships of human settlements with hydroclimatic settings between the pre-Longshan and Longshan periods. The results indicate that the site distribution, site density and hydroclimatic conditions exhibited significant shifts during the pre-Longshan and Longshan periods. In the pre-Longshan period, the intense East Asian summer monsoon and abundant monsoon-related precipitation caused widespread development of lakes and marshes in the lower Yellow River floodplain. As a result, the circumjacent highlands of the lower Yellow River floodplain contained concentrated human settlements. However, the persistent weakening of the East Asian summer monsoon and consequent precipitation decline, in conjunction with accelerated soil erosion due to decreasing forest vegetation and strengthening of human activities on the upstream Loess Plateau in the Longshan period, are likely to have jointly caused both shrinking and faster filling of preexisting lakes and marshes. Subsequently, a large area of arable land had been created in the lower Yellow River floodplain and thus was occupied by locally rapid increasing population, resulting in the notable spatial expansion of human settlements during the Longshan period.

Integrating multilayer perceptron neural nets with hybrid ensemble classifiers for deforestation probability assessment in Eastern India

The rapid expansion of human settlement, agricultural land and roads because of population growth in several regions of the world has contributed to the depletion of forest land. In this study, novel ensemble intelligent approaches using bagging, dagging and rotation forest (RTF) as meta classifiers of multilayer perceptron (MLP) were used to predict spatial deforestation probability (DP) in Gumani Basin, India. The success rate and correctness of prediction of the ensemble models were compared with MLP. A total of 1000 deforested pixels and 14 deforestation determining factors (DDFs) were used. The ensemble models were trained using 70% of the deforested pixels and validated with the remaining 30%. DDFs were chosen by applying the information gain ratio and Relief-F test methods. Distance to settlement, population growth and distance to roads were the most important factors. The results of DP modelling demonstrated that nearly 16.82%–12.64% of the basin had very high DP. All four models created DP maps with reasonable prediction accuracy and goodness of fit, but the best map was produced by MLP-bagging. The accuracy of the MLP neural net model was increased 2-3% after ensemble with the hybrid meta classifiers (RTF, bagging and dagging). The proposed method could be used for deforestation prediction in other areas having similar geo-environmental conditions. Furthermore, the findings might be used as a basis for future research and could help planners in forest management.

Spatial and Temporal Human Settlement Growth Differentiation with Symbolic Machine Learning for Verifying Spatial Policy Targets: Assiut Governorate, Egypt as a Case Study

Since 2005, Egypt has a new land-use development policy to control unplanned human settlement growth and prevent outlying growth. This study assesses the impact of this policy shift on settlement growth in Assiut Governorate, Egypt, between 1999 and 2020. With symbolic machine learning, we extract built-up areas from Landsat images of 2005, 2010, 2015, and 2020 and a Landscape Expansion Index with a new QGIS plugin tool (Growth Classifier) developed to classify settlement growth types. The base year, 1999, was produced by the national remote sensing agency. After extracting the built-up areas from the Landsat images, eight settlement growth types (infill, expansion, edge-ribbon, linear branch, isolated cluster, proximate cluster, isolated scattered, and proximate scattered) were identified for four periods (1999:2005, 2005:2010, 2010:2015, and 2015:2020). The results show that prior to the policy shift of 2005, the growth rate for 1999–2005 was 11% p.a. In all subsequent periods, the growth rate exceeded the target rate of 1% p.a., though by varying amounts. The observed settlement growth rates were 5% (2005:2010), 7.4% (2010:2015), and 5.3% (2015:2020). Although the settlements in Assiut grew primarily through expansion and infill, with the latter growing in importance during the last two later periods, outlying growth is also evident. Using four class metrics (number of patches, patch density, mean patch area, and largest patch index) for the eight growth types, all types showed a fluctuated trend between all periods, except for expansion, which always tends to increase. To date, the policy to control human settlement expansion and outlying growth has been unsuccessful.

Predicting the deforestation probability using the binary logistic regression, random forest, ensemble rotational forest, REPTree: A case study at the Gumani River Basin, India

Rapid population growth and its corresponding effects like the expansion of human settlement, increasing agricultural land, and industry lead to the loss of forest area in most parts of the world especially in such highly populated nations like India. Forest canopy density (FCD) is a useful measure to assess the forest cover change in its own as numerous works of forest change have been done using only FCD with the help of remote sensing and GIS. The coupling of binary logistic regression (BLR), random forest (RF), ensemble of rotational forest and reduced error pruning trees (RTF-REPTree) with FCD makes it more convenient to find out the deforestation probability. Advanced vegetation index (AVI), bare soil index (BSI), shadow index (SI), and scaled vegetation density (VD) derived from Landsat imageries are the main input parameters to identify the FCD. After preparing the FCDs of 1990, 2000, 2010 and 2017 the deforestation map of the study area was prepared and considered as dependent parameter for deforestation probability modelling. On the other hand, twelve deforestation determining factors were used to delineate the deforestation probability with the help of BLR, RF and RTF-REPTree models. These deforestation probability models were validated through area under curve (AUC), receiver operating characteristics (ROC), efficiency, true skill statistics (TSS) and Kappa co-efficient. The validation result shows that all the models like BLR (AUC = 0.874), RF (AUC = 0.886) and RTF-REPTree (AUC = 0.919) have good capability of assessing the deforestation probability but among them, RTF-REPTree has the highest accuracy level. The result also shows that low canopy density area i.e. not under the dense forest cover has increased by 9.26% from 1990 to 2017. Besides, nearly 30% of the forested land is under high to very high deforestation probable zone, which needs to be protected with immediate measures.

AI-based identification of low-frequency debris flow catchments in the Bailong River basin, China

Debris flow is a major geohazard in mountainous regions and poses a significant threat to life and property. The damage caused by debris flows have increased with the expansion of human settlements and activity into the mountainous regions of China. In regards to risks from debris flows, previously unrecognized low-frequency debris flow catchments constitute an especially significant threat. According to our investigation, only about 500 catchments have debris flow records in >2000 catchments of Bailong River basin. The main purpose of this paper is to introduce a new methodology using Artificial Intelligence (AI) that can simultaneously input parameters related to geomorphological conditions and material conditions to better distinguish low-frequency debris flow catchments (LFDs) from medium-high frequency debris flow catchments (MHFDs). A total of 449 prototypical debris flow catchments, 15 parameters, and 9 commonly used learning machines were used to build identification models. Debris flow catchments are divided into 4 cases (LO1-LO4) based on different sample ratios of LFDs and MHFDs, which are input into each classifier one by one. Based on model evaluation, the CHAID model in the case LO2 performs best, which only uses five parameters (formation lithology index, land use index, vegetation coverage index, drainage density and landslide density index) to predict LFDs. The results indicate that LFDs are mainly distributed in areas with less landslide distribution and better vegetation coverage compared with MHFDs. However, the distribution of LFDs is concentrated on FLI (formation lithology index) =4, which is the weak lithology area. The tree classifier seems to be better at classifying fluvial processes. The model developed in this paper can help us quickly find LFDs in similar areas, and help to assess the risk of debris flows.