Wyniki wyszukiwania - BazTech

1

Snow water equivalent prediction in a mountainous area using hybrid bagging machine learning approaches

Khosravi Khabat, Golkarian Ali, Omidvar Ebrahim, Hatamiafkoueieh Javad, Shirali Masoud

Acta Geophysica

|

2023

|

Vol. 71, no. 2

1015--1031

EN

Snow Water Equivalent (SWE) is one of the most critical variables in mountainous watersheds and needs to be considered in water resources management plans. As direct measurement of SWE is difficult and empirical equations are highly uncertain, the present study aimed to obtain accurate predictions of SWE using machine learning methods. Five standalone algorithms of tree-based [M5P and random tree (RT)], rule-based [M5Rules (M5R)] and lazy-based learner (IBK and Kstar) and five novel hybrid bagging-based algorithms (BA) with standalone models (i.e., BA-M5P, BA-RT, BA-IBK, BA-Kstar and BA-M5R) were developed. A total of 2550 snow measurements were collected from 62 snow and rain-gauge stations located in 13 mountainous provinces in Iran. Data including ice beneath the snow (IBS), fresh snow depth (FSD), length of snow sample (LSS), snow density (SDN), snow depth (SD) and time of falling (TS) were measured. Based on the Pearson correlation between inputs (IBS, FSD, LSS, SDN, SD and TS) and output (SWE), six different input combinations were constructed. The dataset was separated into two groups (70% and 30% of the data) by a cross-validation technique for model construction (training dataset) and model evaluation (testing dataset), respectively. Different visual and quantitative metrics (e.g., Nash–Sutclife efficiency (NSE)) were used for evaluating model accuracy. It was found that SD had the highest correlation with SWE in Iran (r=0.73). In general, the bootstrap aggregation (i.e., bagging) hybrid machine learning methods (BA-M5P, BA-RT, BA-IBK, BA-Kstar and BA-M5R) increased prediction accuracy when compared to each standalone method. While BA-M5R had the highest prediction accuracy (NSE=0.83) (considering all six input variables), BA-IBK could predict SWE with high accuracy (NSE=0.71) using only two input variables (SD and LSS). Our findings demonstrate that SWE can be accurately predicted through a variety of machine learning methods using easily measurable variables and may be useful for applications in other mountainous regions across the globe.

2

A geospatial analysis of long-term trends in snow depth in the Hindu Kush Himalayan region: 1999–2019

Conyers Zella, Roy Shouraseni Sen

Acta Geophysica

|

2023

|

Vol. 71, no. 5

2535--2544

EN

The Hindu Kush Himalaya (HKH) region is a major source of natural resources, like fresh water, for communities throughout south Asia. Monitoring the spatial patterns of climate variables throughout the region can help better understand and predict the future of this critical resource. In situ daily snow depth measurements from 1999 to 2019 were utilized to detect spatial patterns of the long-term trends in snow depths across the HKH region. The geospatial analysis included the use of emerging hot spots analysis. The results of our analysis revealed three broad regional clusters of long-term trends, including western, central, and eastern regions. Both eastern and western regions displayed declining snow depths, whereas the central region experienced areas of increasing snow depths. We also examined the localized long-term trends of snow depth around mega cities in the region, to delineate the role of urbanization on snow cover. The local level trends around the mega cities showed variable trends, determined by elevation and local pollution levels.

3

Klasyfikacja zim w polskiej stacji polarnej w Hornsundzie (SW Spitsbergen) w okresie 1978/1979-2014/2015

Caputa Z., Leszkiewicz J.

Problemy Klimatologii Polarnej

|

2015

|

Nr 25

169--178

PL

Zmiany klimatu w ostatnich kilkudziesięciu latach w rejonie Hornsundu (SW Spitsbergen) wynikają głównie ze zmiany warunków pogodowych zim. Dlatego temperatura powietrza i grubość pokrywy śnieżnej, podstawowe elementy meteorologiczne charakteryzujące zimy, posłużyły do przeprowadzenia ich klasyfikacji. W wyniku standaryzacji tych elementów z wielolecia 1978/1979-2014/2015 wydzielono pięć typów zim: typowe (typ 0), mroźne i śnieżne (1), łagodne i śnieżne (2), mroźne i mało śnieżne (3) oraz łagodne i mało śnieżne (4). Taka klasyfikacja pozwoliła uporządkować zimy, określić tendencje ich zmian, scharakteryzować typy oraz dodatkowo, daje możliwość porównywania zim w różnych obszarach polarnych i wysokogórskich. W badanym okresie stwierdzono zmianę typu z zim mroźnych i śnieżnych na łagodne i mało śnieżne.

EN

The progressive warming of climate in recent decades in the region of Hornsund (SW Spitsbergen) has resulted mainly from a change in the nature of winters. Air temperature and snow depths, the basic elements characterizing the meteorological winter, were used to develop the winter classification. As a result of the standardization of the data, five types of winter have been distinguished: typical winter (type 0) and four the other four types of winter: freezing, snowy winter (1), mild, snowy winter (2), freezing winter with little snow (3), mild winter with little snow (4). In the period of 1978/1979-2014/2015 the following have been found out the change from the freezing and snowy winters to mild winters with little snow.