Publications by authors named "Ali Torabi Haghighi"

10 Publications

  • Page 1 of 1

Integration of hard and soft supervised machine learning for flood susceptibility mapping.

J Environ Manage 2021 Aug 4;291:112731. Epub 2021 May 4.

Team Soil, Water and Land Use, Wageningen Environmental Research, Droevendaalsesteeg 3, 6708RC, Wageningen, the Netherlands; Civil, Surveying and Environmental Engineering, The University of Newcastle, Callaghan, 2308, Australia.

Flooding is a destructive natural phenomenon that causes many casualties and property losses in different parts of the world every year. Efficient flood susceptibility mapping (FSM) can reduce the risk of this hazard, and has become the main approach in flood risk management. In this study, we evaluated the prediction ability of artificial neural network (ANN) algorithms for hard and soft supervised machine learning classification in FSM by using three ANN algorithms (multi-layer perceptron (MLP), fuzzy adaptive resonance theory (FART), self-organizing map (SOM)) with different activation functions (sigmoidal (-S), linear (-L), commitment (-C), typicality (-T)). We used integration of these models for predicting the spatial expansion probability of flood events in the Ajichay river basin, northwest Iran. Inputs to the ANN were spatial data on 10 flood influencing factors (elevation, slope, aspect, curvature, stream power index, topographic wetness index, lithology, land use, rainfall, and distance to the river). The FSMs obtained as model outputs were trained and tested using flood inventory datasets earned based on previous records of flood damage in the region for the Ajichay river basin. Sensitivity analysis using one factor-at-a-time (OFAT) and all factors-at-a-time (AFAT) demonstrated that all influencing factors had a positive impact on modeling to generate FSM, with altitude having the greatest impact and curvature the least. Model validation was carried out using total operating characteristic (TOC) with an area under the curve (AUC). The highest success rate was found for MLP-S (92.1%) and the lowest for FART-T (75.8%). The projection rate in the validation of FSMs produced by MLP-S, MLP-L, FART-C, FART-T, SOM-C, and SOM-T was found to be 90.1%, 89.6%, 71.7%, 70.8%, 83.8%, and 81.1%, respectively. While integration of hard and soft supervised machine learning classification with activation functions of MLP-S and MLP-L showed a strong flood prediction capability for proper planning and management of flood hazards, MLP-S is a promising method for predicting the spatial expansion probability of flood events.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jenvman.2021.112731DOI Listing
August 2021

Battling Water Limits to Growth: Lessons from Water Trends in the Central Plateau of Iran.

Environ Manage 2021 Jul 7;68(1):53-64. Epub 2021 Apr 7.

Council on Middle East Studies, The Whitney and Betty MacMillan Center for International and Area Studies, Yale University, New Haven, USA.

The Zayandeh-Rud River Basin in the central plateau of Iran continues to grapple with water shortages due to a water-intensive development path made possible by a primarily supply-oriented water management approach to battle the water limits to growth. Despite inter-basin water transfers and increasing groundwater supply, recurring water shortages and associated tensions among stakeholders underscore key weaknesses in the current water management paradigm. There was an alarming trend of groundwater depletion in the basin's four main aquifers in the 1993-2016 period as indicated by the results of the Mann-Kendall3 (MK3) test and Innovative Trend Analysis (ITA) of groundwater volume. The basin's water resources declined by more than 6 BCM in 2016 compared to 2005 based on the equivalent water height (EWH) derived from monthly data (2002-2016) from the GRACE. The extensive groundwater depletion is an unequivocal evidence of reduced water availability in the face of growing basin-wide demand, necessitating water saving in all water use sectors. Implementing an integrated water resources management plan that accounts for evolving water supply priorities, growing demand and scarcity, and institutional changes is an urgent step to alleviate the growing tensions and preempt future water insecurity problems that are bound to occur if demand management approaches are delayed.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00267-021-01447-0DOI Listing
July 2021

Complex dynamics of water quality mixing in a warm mono-mictic reservoir.

Sci Total Environ 2021 Jul 1;777:146097. Epub 2021 Mar 1.

Water, Energy and Environmental Engineering Research Unit, University of Oulu, P.O. Box 4300, FIN-90014 Oulu, Finland.

Cycling of water quality constituents in lakes is affected by thermal stratification and homo-thermal conditions and other factors such as oligotrophication, eutrophication, and microbial activities. In addition, hydrological variability can cause greater differences in water residence time and cycling of constituents in man-made lakes (reservoirs) than in natural lakes. Thus, investigations are needed on vertical mixing of constituents in new impounded reservoirs, especially those constructed to supply domestic water. In this study, sampling campaigns were conducted in the Sabalan reservoir, Iran, to investigate vertical changes in constituent concentrations during the year in periods with thermal stratification and homo-thermal conditions. The results revealed incomplete mixing of constituents, even during cold months when the reservoir was homo-thermal. These conditions interacted to create a bottom-up regulated reservoir with sediment that released settled pollutants, impairing water quality in the Sabalan reservoir during both thermal stratification and homo-thermal conditions. Analysis of total nitrogen and total phosphorus concentrations revealed that the reservoir was eutrophic. External pollution loads, internal cycling of pollutants diffusing out from bottom sediments, reductions in inflow to the reservoir, and reservoir operations regulated vertical mixing and concentrations of constituents in the Sabalan reservoir throughout the year.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.scitotenv.2021.146097DOI Listing
July 2021

Vegetation height estimation using ubiquitous foot-based wearable platform.

Environ Monit Assess 2020 Nov 21;192(12):774. Epub 2020 Nov 21.

Water, Energy and Environmental Engineering Research Unit, University of Oulu, Oulu, Finland.

Vegetation height plays a key role in many environmental applications such as landscape characterization, conservation planning and disaster management, and biodiversity assessment and monitoring. Traditionally, in situ measurements and airborne Light Detection and Ranging (LiDAR) sensors are among the commonly employed methods for vegetation height estimation. However, such methods are known for their high incurred labor, time, and infrastructure cost. The emergence of wearable technology offers a promising alternative, especially in rural environments and underdeveloped countries. A method for a locally designed data acquisition ubiquitous wearable platform has been put forward and implemented. Next, a regression model to learn vegetation height on the basis of attributes associated with a pressure sensor has been developed and tested. The proposed method has been tested in Oulu region. The results have proven particularly effective in a region where the land has a forestry structure. The linear regression model yields (r = 0.81 and RSME = 16.73 cm), while the use of a multi-regression model yields (r = 0.82 and RSME = 15.73 cm). The developed approach indicates a promising alternative in vegetation height estimation where in situ measurement, LiDAR data, or wireless sensor network is either not available or not affordable, thus facilitating and reducing the cost of ecological monitoring and environmental sustainability planning tasks.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s10661-020-08712-5DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7680353PMC
November 2020

Development of novel hybridized models for urban flood susceptibility mapping.

Sci Rep 2020 07 31;10(1):12937. Epub 2020 Jul 31.

Water, Energy and Environmental Engineering Research Unit, University of Oulu, Oulu, Finland.

Floods in urban environments often result in loss of life and destruction of property, with many negative socio-economic effects. However, the application of most flood prediction models still remains challenging due to data scarcity. This creates a need to develop novel hybridized models based on historical urban flood events, using, e.g., metaheuristic optimization algorithms and wavelet analysis. The hybridized models examined in this study (Wavelet-SVR-Bat and Wavelet-SVR-GWO), designed as intelligent systems, consist of a support vector regression (SVR), integrated with a combination of wavelet transform and metaheuristic optimization algorithms, including the grey wolf optimizer (GWO), and the bat optimizer (Bat). The efficiency of the novel hybridized and standalone SVR models for spatial modeling of urban flood inundation was evaluated using different cutoff-dependent and cutoff-independent evaluation criteria, including area under the receiver operating characteristic curve (AUC), Accuracy (A), Matthews Correlation Coefficient (MCC), Misclassification Rate (MR), and F-score. The results demonstrated that both hybridized models had very high performance (Wavelet-SVR-GWO: AUC = 0.981, A = 0.92, MCC = 0.86, MR = 0.07; Wavelet-SVR-Bat: AUC = 0.972, A = 0.88, MCC = 0.76, MR = 0.11) compared with the standalone SVR (AUC = 0.917, A = 0.85, MCC = 0.7, MR = 0.15). Therefore, these hybridized models are a promising, cost-effective method for spatial modeling of urban flood susceptibility and for providing in-depth insights to guide flood preparedness and emergency response services.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-69703-7DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7395144PMC
July 2020

RiMARS: An automated river morphodynamics analysis method based on remote sensing multispectral datasets.

Sci Total Environ 2020 Jun 15;719:137336. Epub 2020 Feb 15.

Water, Energy and Environmental Engineering Research Unit, University of Oulu, Oulu, Finland.

Assessment and monitoring of river morphology own an important role in river engineering; since, changes in river morphology including erosion and sedimentation affect river cross-sections and flow processes. An approach for River Morphodynamics Analysis based on Remote Sensing (RiMARS) was developed and tested on the case of Mollasadra dam construction on the Kor River, Iran. Landsat multispectral images obtained from the open USGS dataset are used to extract river morphology dynamics by the Modified Normalized Difference Water Index (MNDWI). RiMARS comes with a river extraction module which is independent of threshold segmentation methods to produce binary-level images. In addition, RiMARS is equipped with developed indices for assessing the morphological alterations. Five characteristics of river morphology (spatiotemporal Sinuosity Index (SI), Absolute Centerline Migration (ACM), Rate of Centerline Migration (RCM), River Linear Pattern (RLP), and Meander Migration Index (MMI)), are applied to quantify river morphology changes. The results indicated that the Kor River centerline underwent average annual migration of 40 cm to the southwest during 1993-2003 (pre-construction impact), 20 cm to the northeast during 2003-2011, and 40 cm to the south-west during 2011-2017 (post-construction impact). Spatially, as the Kor River runs towards the Doroudzan dam, changes in river morphology have increased from upstream to downstream; particularly evident where the river flows in a plain instead of the valley. Based on SI values, there was a 5% change in the straight sinuosity class in the pre-construction period, but an 18% decrease in the straight class during the post-construction period. Here we demonstrate the application of RiMARS in assessing the impact of dam construction on morphometric processes in Kor River, but it can be used to assess other riverine changes, including tracking the unauthorized water consumption using diverted canals. RiMARS can be applied on multispectral images.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.scitotenv.2020.137336DOI Listing
June 2020

Flash-flood hazard assessment using ensembles and Bayesian-based machine learning models: Application of the simulated annealing feature selection method.

Sci Total Environ 2020 Apr 21;711:135161. Epub 2019 Nov 21.

Water, Energy and Environmental Engineering Research Unit, University of Oulu, P.O. Box 4300, FIN-90014 Oulu, Finland.

Flash-floods are increasingly recognized as a frequent natural hazard worldwide. Iran has been among the mostdevastated regions affected by the major floods. While the temporal flash-flood forecasting models are mainly developed for warning systems, the models for assessing hazardous areas can greatly contribute to adaptation and mitigation policy-making and disaster risk reduction. Former researches in the flash-flood hazard mapping have heightened the urge for the advancement of more accurate models. Thus, the current research proposes the state-of-the-art ensemble models of boosted generalized linear model (GLMBoost) and random forest (RF), and Bayesian generalized linear model (BayesGLM) methods for higher performance modeling. Furthermore, a pre-processing method, namely simulated annealing (SA), is used to eliminate redundant variables from the modeling process. Results of the modeling based on the hit and miss analysis indicates high performance for both models (accuracy = 90-92%, Kappa = 79-84%, Success ratio = 94-96%, Threat score = 80-84%, and Heidke skill score = 79-84%). The variables of distance from the stream, vegetation, drainage density, land use, and elevation have shown more contribution among others for modeling the flash-flood. The results of this study can significantly facilitate mapping the hazardous areas and further assist watershed managers to control and remediate induced damages of flood in the data-scarce regions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.scitotenv.2019.135161DOI Listing
April 2020

Fog-water harvesting Capability Index (FCI) mapping for a semi-humid catchment based on socio-environmental variables and using artificial intelligence algorithms.

Sci Total Environ 2020 Mar 20;708:135115. Epub 2019 Nov 20.

Water, Energy and Environmental Engineering Research Unit, University of Oulu, P.O. Box 4300, FIN-90014 Oulu, Finland.

Fog is an important component of the water cycle in northern coastal regions of Iran. Having accurate tools for mapping the precise spatial distribution of fog is vital for water harvesting within integrated water resources management in this semi-humid region. In this study, environmental variables were considered in prediction mapping of areas with high concentrations of fog in the Vazroud watershed, Iran. Fog probability maps were derived from four artificial intelligence algorithms (Generalized Linear Model, Generalized Additive Model, Generalized Boosted Model, and Generalized Dissimilarity Model). Models accuracy were assessed using Receiver Operating characteristic Curve (ROC). Three social variables were also selected according to their relevance for fog suitability mapping. Finally, Fog-water harvesting Capability Index (FCI) maps were produced by multiplying fog probability by fog suitability maps. The results showed high accuracy in fog probability mapping for the study area, with all models proving capable of identifying areas with high fog concentrations in the south and southeast. For all models, the highest values of importance were obtained for sky view factor and the lowest for slope curvature. Analytic Hierarchy Process results showed the relative importance of social conditioning factors in fog suitability mapping, with the highest weight given to distance to residential area, followed by distance to livestock buildings and distance to road. Based on the fog suitability map, southeast and southern parts of the study area are most suitable for fog water harvesting. The fog spatial distribution maps obtained can increase fog water harvesting efficiency. They also indicate areas for future study with regions where fog is a critical component in the water cycle.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.scitotenv.2019.135115DOI Listing
March 2020

Impact of managed aquifer recharge structure on river flow regimes in arid and semi-arid climates.

Sci Total Environ 2019 Jul 17;675:429-438. Epub 2019 Apr 17.

Water, Energy and Environmental Engineering Research Unit, University of Oulu, Oulu, Finland.

Managed aquifer recharge (MAR) structure is widely used to expand groundwater resources. In arid regions with flash flooding, MAR can also be used as a flood control structure to decrease peak discharge of rivers. In this paper, we present a method for quantifying the role of MAR in head water systems and assess its impact on the total water balance in a river basin. The method is based on rainfall-runoff modeling, reservoir flood routing, recharge analysis and river flow analysis. For the case selected, Kamal Abad MAR in Lake Maharlou basin in southern Iran, we analyzed changes in the downstream river regime using two scenarios (with MAR and without MAR) with different return periods. The results revealed a significant impact of MAR on river flow in terms of changes in flow timing, magnitude and variability. With MAR, the ephemeral river studied became disconnected from the main stream, albeit, whereas the case without MAR, floods with return period higher than 10 years would be connected to the downstream. Even though, MAR structures are useful in arid and semi-arid climates for irrigation water supply, their placing and designing need more attention. The developed method can be used to assess the impacts of MAR on river flow and find the best location for it to make the connection of the ephemeral river and downstream river, an issue which has not received much attention in hydrological research.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.scitotenv.2019.04.253DOI Listing
July 2019

Changes in short term river flow regulation and hydropeaking in Nordic rivers.

Sci Rep 2018 11 22;8(1):17232. Epub 2018 Nov 22.

Water Resources and Environmental Engineering Research Unit, PO Box 4300, 90014 University of Oulu, Oulu, Finland.

Quantifying short-term changes in river flow is important in understanding the environmental impacts of hydropower generation. Energy markets can change rapidly and energy demand fluctuates at sub-daily scales, which may cause corresponding changes in regulated river flow (hydropeaking). Due to increasing use of renewable energy, in future hydropower will play a greater role as a load balancing power source. This may increase current hydropeaking levels in Nordic river systems, creating challenges in maintaining a healthy ecological status. This study examined driving forces for hydropeaking in Nordic rivers using extensive datasets from 150 sites with hourly time step river discharge data. It also investigated the influence of increased wind power production on hydropeaking. The data revealed that hydropeaking is at high levels in the Nordic rivers and have seen an increase over the last decade and especially over the past few years. These results indicate that increased building for renewable energy may increase hydropeaking in Nordic rivers.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-018-35406-3DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6250702PMC
November 2018