Дэлгэрэнгүй мэдээлэл

Artificial intelligence has had a significant impact on banking services in the era of rapid technological changes. In this study, we aimed to determine if the selected banks offer their customers AI products by consulting with relevant officials. Additionally, we assessed the consumers' attitudes toward adopting AI in banking services. We provided a survey to examine the perception of the customers of the selected banks. We involved 508 users who took part in the survey, and 487 valid responses for further analysis. A recent study among local banks has shown that the selected banks in our study are using various artificial intelligence products these days. The remaining banks also expressed their willingness to introduce AI supported products and businesses to their customers. According to our research, policymakers should focus on strengthening the perceived usefulness, perceived trust, and attitude toward AI in banking to increase the adoption of AI-enabled banking services. It will improve the customer service among the banks and improve users' confidence in accepting such services.

Заг мод нь говийн бүс нутгийн эко системд чухал үүрэг гүйцэтгэдэг. Өмнөговь аймаг нь заган ойн тархцаар улсдаа хоёрдугаарт ордог бөгөөд нийт нутаг дэвсгэрийн ихэнх хэсэгт хуурайшилт эрчимтэй явагдаж байгаатай холбоотойгоор “Нэг тэрбум мод тарих” төслийн хүрээнд заг модыг нөхөн сэргээх, тарих ажил эрчимтэй явагдаж байгаа бөгөөд заг модыг тариалахад урт хугацааны мэдээнд үндэслэсэн судалгаа хийх нь ихээхэн ач холбогдолтой юм. Уг судалгааны ажлаар хиймэл дагуулын мэдээ болон нөхцөлт функцийн арга, түүнчлэн орчин үед өргөн ашиглагдаж байгаа машин сургалтын арга ашиглан заг модыг тариалах тохиромжтой байдлын судалгааг хийхийг зорьсон. Судалгааны талбай нь Өмнөговь аймгийн нутаг бөгөөд судалгаанд MODIS хиймэл дагуулын 2000-2022 оны мэдээг ашигласан. Судалгааны ажлын хүрээнд MODIS хиймэл дагуулын мэдээнд боловсруулалт хийж, нөхцөлт функцийн аргаар Өмнөговь аймгийн заган ойн зургийг гарган, тариалах тохиромжтой байдлыг тодорхойлсон. Тохиромжтой байдлын үнэлгээний үр дүнгийн хувьд Баяндалай, Хүрмэн сумууд нь бидний өгсөн бүх нөхцөлүүдийг хангаж байгаа тул заг мод тариалахад хамгийн тохиромжтой гэсэн үр дүн гарсан. Мөн машин сургалтын Support vector classification аргыг ашиглан заган ойн ангилал хийхэд таарц нь 80%-тай гарсан нь өндөр үр дүнтэй байсан.

Хураангуй: Кредит скорингийн шинжилгээ нь санхүүгийн үйлчилгээ үзүүлэгч байгууллагууд зээлдэгчдэд эрсдэлгүй буюу хамгийн бага эрсдэлтэй зээл олгоход тусалдаг. Сүүлийн үеийн судалгааны ажлуудын үр дүнгээс харахад машин сургалтын аргууд түүн дотроо холимог сургалтын /ensemble learning/ аргаар боловсруулсан загварууд энэ салбарт тэргүүлэх байр суурь эзэлж байна. Бид энэхүү судалгааны ажлаараа А банк бус санхүүгийн байгууллагын 1650 зээлдэгчийн өгөгдлийг ашиглан холимог сургалтын хоёр /XGBoost, Catboost/ алгоритмаар кредит скорингийн загвар боловсруулж, харьцуулах оролдлого хийсэн. Судалгааны ажлын үр дүнгээс харахад XGBoost алгоритм ашиглан боловсруулсан загварын үр дүн алдааны матриц (confusion matrix), нарийвчлал (accuracy), percision, recall, f1-score, ROC муруй зэрэг үзүүлэлтүүд хүлээн зөвшөөрөгдөхүйц гарсан.

Sangaku problem is one of Japanese Temple Geometry problems which was studied in Hidetoshi Fukugawa[1]. One of the Sangaku problem is packing 6 equal circles in rectangle of 1:1.934798 size. We examine the problem from a view point of optimization theory and algorithm. We show that Sangaku optimization problem belongs to a class of nonconvex optimization and propose a penalty method for solving the problem numerically. In numerical expirements, we consider equal and unequal 6 circles. Computational results obtained on Python Jupyter Notebook are provided

Umnugobi province ranks second in the country in terms of larch forests, and the entire territory has been intensively drying up and desertification in recent years. Also, within the framework of the "One Billion Tree Planting" project, the restoration and planting of saxaul trees is starting. It is vital to plant the right trees in the right places and for the saxaul tree, the basis of successful planting is to determine the area to be planted by studying long-term data. This study aims to study the feasibility of using satellite data, conditional function methods, and machine learning tools widely used in modern times, to cultivate saxaul trees. As a result of the suitability evaluation, it was found that Bayandalai and Khurmen bullets of Umnogobi province are the most suitable for planting zag. In addition, the machine learning support vector classification method was used to classify the areas with and without saxaul trees in Umnugobi province with an accuracy of 80%.

Abstract: With the increasing availability of various types of data, anomaly detection in massive datasets has seen growing focus in many fields. Anomaly detection is one of the techniques used to identify unusual patterns or outliers. There are various methods and algorithms used for anomaly detection, including statistical and machine learning methods. Sudden Stratospheric Warming (SSW) is a meteorological phenomenon that refers to a rapid increase in temperatures in the stratosphere, usually occurring in the middle to late winter. One of the notable impacts of SSW is the occurrence of anomalous cold air outbreaks and enhanced precipitation in northern Eurasia and South Asia. Accurately predicting SSWs could help improve weather forecasting and provide more advanced warnings for extreme weather events (dzud etc). This study focuses on developing algorithm that to detect SSW events by using high dimensional satellite data. We applied deep learning and statistical mixed algorithms for modeling and detecting anomalies. The results show that the proposed method has high accuracy for both prediction and anomaly detection. Keywords: anomaly detection, neural networks, sudden stratospheric warming

Saxual trees play an important role in the ecosystem of the Gobi region. Umnugobi province is second in the country in terms of saxaul forests, and the entire territory is rapidly drying, and within the framework of the "One Billion Tree Planting" project, tree restoration and planting is in full swing. Research based on long-term data is of great importance in cultivating saxaul trees. This study aims to study the feasibility of using satellite data, conditional function methods, and machine learning tools widely used in modern times, to cultivate saxaul trees. As for the suitability evaluation results, Bayandalai and Khurmen bullets have the results for suitability saxaul planting because they are using everything we have conditions. Also, when using the Support Vector classification method of machine learning, it was highly effective with 80% accuracy.

Mongolian area is a dry, cold climate, and geographical features are associated with the fragility of natural ecosystems, also global climate change may have a strong impact on the Mongolian semi-desert zone. Understanding and monitoring Gross Primary Production (GPP) is a critical component of exploring the impact of desertification, and dust storms in the study area. The purpose of this study is to monitor GPP over the Mongolian semi-desert zone. We used MODIS GPP product and a machine-learning-based GPP (SVR-GPP) from 2000 to 2020. We applied a time series analysis to derive GPP over Mongolian across natural ecosystem zone semi-desert zones for years 2000-2020 and predict its future trends until 2030. The output GPP maps from the approach was validated by comparing them with the SVR GPP for the natural zone of semi-desert (r2=0.92). The results indicate that the GPP of the Mongolia values is high in range in semidesert can be between the range 0.01-1.3 gC m−2 day−1. The results of the research suggest that the proposed approach using SVR-GPP data is suitable for monitoring GPP over a semi-desert area and contributing to the control of the carbon cycle.

Abstract This study investigates of the grassland changes in Mongolian steppe area. Panel data analysis are proposed for estimating the relationship between grassland and biophysical parameters such as Land Surface Temperature (LST), Normalized Difference Water Index (NDWI), Elevation, and Slope. The study area is Dornod province which is one of the largest steppes in Mongolia. The data from randomly selected ten locations over this area during the growing season (April to September) from 2003 to 2018. The Normalized Difference Vegetation Index (NDVI) is used to characterize the grassland changes over the study area. The data were obtained from the various satellite. Multiple linear regression, fixed effects panel regression and random effects panel regression were applied to derive an empirical relationship between the grassland and the biophysical parameters. Statistical significance tests show that random effects model’s coefficients represent the relationships better. According to the results, NDWI has a strong positive dependence on NDVI, whereas the LST has a weak and negative effects. Though the Slope had little effect and the Elevation showed a weak positive relationship. The output compared with satellite data for 20% and agreement was 83% at 5% significance level. The results suggest that the proposed model is suitable for monitoring grassland change, and to examine the factors that contribute to the grassland variations. Keywords: Grassland dynamics; Mongolian steppe, Time-series and Cross-section data; Panel data analysis, Fixed and Random effects model

The purpose of this study, we use vegetation index with time series analysis and determine the predicted future prospects and forecasting for an agricultural area. The study area is situated in the steppe region Dornod province, north-eastern part of Mongolia. In this research, we choose the ARIMA (Autoregressive integrated moving average) model, one of the best-known methods of time series analysis using the NDVI (Normalized Difference Vegetation Index) vegetation index from MODIS remote sensing satellite data between 2010 to 2020. The analysis was performed by Python Jupyter Notebook, ArcGIS, and Envi classic. Validations of this model were issued every four season and the average of agreement is 62 percent.

Monitoring carbon storage in the forest is important for tracking ecosystem functionalities and climate change impacts. Estimation of GPP and study of the carbon cycle in Mongolia is essential. The main aim of this study is to develop an estimation approach for monitoring GPP (Gross Primary Production) for Mongolian forests using satellite data. GPP takes into account how much carbon dioxide (CO2) is taken in by vegetation during photosynthesis GPP and how much CO2 is given off during respiration, which is the process by which organisms use food to produce energy. The study focused on the Remote Sensing data and biomass data from ground truth measurements in 2018. Output MONGPP for 2000-2020 data were related to NDVI and LST from MODIS and agreement was 69% and 41% respectively. Thus, the estimation of carbon stocks of different climate zones would help in appropriate decisionmaking on carbon management in the region. This study will contribute to understanding the dynamics of carbon stocks in relation to the key factors for the sustainable management of forest carbon.

Steppe fires caused by nature or humans are considered among the most dangerous and devastating disasters around the world. The purpose of this study is to develop a model for predicting steppe fire using random forest classification for natural fires. The study area is Dornod province located in the eastern part of Mongolia. Landcover is mainly a steppe area. There is a high number of fire events each year in springtime. We used satellite data such as the normalized difference vegetation index, land surface temperature, and modified soil-adjusted vegetation index for the spring of the years 2015-2022. Digital elevation model and climate data such as air temperature, precipitation, and wind speed were applied in this study. The overall accuracy of the random forest algorithm was 81%. The results showed that the random forest classification method can be used to predict steppe fires and monitor environmental issues in Mongolia.

The purpose of the research is to develop and compare land cover classification methods using linear mixing model (LMM) and random forest in Google Earth Engine (GEE). The study area is Khangal soum of Bulgan province and the site is situated in a forest-steppe zone with mountains and hills. The area such land cover types as bare land, forest, and grass. Spectral bands 2, 3, 4, and 5 of Landsat 8 data of 2018 and ground truth data have been used in the research. Result of the LMM was compared with the result of the random forest methodology along with ground truth measurements. The overall accuracy of the LMM using ground truth data was 75.2%. Unlike the model, the result of the random forest technique and ground observation data had a good agreement, resulting in overall accuracy of 94.4%.

Land Cover/ Land Use(LCLU) is changing from year to year due to many factors such as urbanization, mining, agriculture and climate change. Using Land cover classification methodologies is important for land related studies. The aim of the study was to propose and compare land cover classification using Linear Mixing Model (LMM), and Random forest (RF). Study area is Khangal soum of Bulgan province and is dominated by forest-steppe zone with mountains and hills. The area covered by bare land, forest and grass classes. Spectral bands 2,3,4 and 5 of the Landsat8 data for 2018-2020 and ground truth data were used in the research. The results of LMM show that there were 97.5% for larch, 60% for birch, 46.6% for vegetation, and 84% for non-forested areas. Outputs of the linear mixing model was compared with outputs data from random forest methodology. Random forest is more useful for LCLU study.

This article analyzes the implementation of differentiated instruction in teaching astronomy programs and develops a methodology for integrating it into natural science education. Astronomy is a natural science that studies celestial objects and phenomena. Using differentiated instruction and multiple teaching strategies is essential to support all students learning. All students learn differently, so differentiated instruction techniques can include scientific experimentation, historical investigation, discussion, and debate; research projects; problem-solving; simulations, models, or demonstrations; and the creation of products or performances. Differentiated instruction permits each individual to get the information, abilities, perspectives, and qualities essential to shaping the universe whole. Astronomy is closely linked with education, pedagogy, and mental health. The current paper draws learning style differences (including multiple intelligence of Howard Gardner and VAK preferences) to identify practical, supportive approaches and critical conceptual frameworks applied to astronomy education. Theory and research findings are reviewed, highlighting the importance of knowing the differences between students and focusing on motivational issues. Research or inquiry-based assignments target those in which students are required to find, analyze, and use various information sources, explore an issue, solve a problem, and create new knowledge. They are intrapersonal students. The class discussion allows linguistic students to share their ideas out loud and use problem-solving skills and critical thinking to answer essential questions relating to the subject matter. The technology-based lesson incorporates video, research, and the creation of a presentation that targets visual and auditory learners because it relays information so that students can listen to facts and connect them with pictures on the screen. Kinesthetic and visual learners with a logical-mathematical ability like digital imaging spend most of their time in front of a computer analyzing large amounts of data, and it can be delightful. The modeling/demonstration helps students visualize the planets’ sizes and distances from the sun. It allows students to connect understanding with various student experiences, cultures, interests, and perspectives. Other differentiated instruction techniques that can be incorporated involve a wide range of activities or assignments or creating different degrees of difficulty for appropriate challenge levels while maintaining the same content goals. These strategies should be incorporated into daily activities, projects, and assessments based on each student’s individual needs and level of readiness. Keywords: multiple intelligences, visual, auditory, kinesthetic, readiness

Riverbank erosion is an important topic in environmental research. Although several methods have been used to prevent erosion and balance ecosystems, both are still very challenging issues. We propose three different adaptation approaches to control riverbank erosion in the steppe area. The area has been affected by dramatic erosion over the past several years due to water flow and other external effects. The approaches were based on bioengineering and mechanical methods that were different in terms of the erosion rate and slope of the riverbank, the velocity and intensity of water flow, and the mechanical properties of the soil and plant species. Cost benefit analysis (CBA) and sensitivity analysis were applied to estimate and compare the approaches. The most appropriate approaches were selected by comparing the net present value (NPV), the benefit-cost ratio (BCR), and the internal rate of return (IRR), which are the main indicators of CBA. The CBA results indicated that all the approaches had positive benefits in 2020-2030. The most economically and environmentally beneficial approach was Approach-3 (bioengineering method). A Monte Carlo sensitivity analysis demonstrated that the NPV of Approach-3 was positive in both scenarios of the pessimistic and optimistic cases of the discount rate. Monte Carlo analysis with 500 simulations was performed to obtain the future NPV. The results reveal that bioengineering methods for riverbank erosion control have higher environmental benefits and are more suitable in steppe areas.

Монгол бол нүүдэлчдийн уламжлалт ахуй орчин үеийн хотын амьдралын хэв маягтай зэрэгцэн оршдог цөөхөн хүн амтай, өргөн уудам газар нутагтай хөгжиж буй орон юм. Нутаг дэвсгэрийн хэмжээнд уур амьсгалын буюу байгалийн давагдашгүй хүчин зүйлүүд аль хэдийн тохиолдож, цаашид нэмэгдэх хандлагатай байгаагийн хажуугаар нийгэм-эдийн засгийн нөхцөл, хүний үйл ажиллагаа, хандлагаас шалтгаалж МАА-н салбарын эмзэг, эрсдэлтэй байдал нэмэгдэж байна. ҮТХН Түншлэлийн Уур амьсгалын арга хэмжээг хэрэгжүүлэх багц төсөл (CAEP) нь 2019 оны 9-р сараас 46 олон улсын түншүүдийн санхүү, техникийн дэмжлэгтэйгээр 63 гишүүн орнуудын Парисын хэлэлцээрийг хэрэгжүүлэх үндэсний тодорхойлсон хувь нэмрийн зорилтоо биелүүлэх болон ахиулахад нь, мөн түргэвчлэн хэрэгжүүлэхэд хэрэгцээтэй чадавхийг дэмжих гэсэн хоёр ерөнхий зорилготойгоор хэрэгжиж байна. Энэхүү зөвлөх ажлын хүрээнд мал аж ахуйн салбарын уур амьсгалд ухаалгаар дасан зохицох арга хэмжээнүүдийг олон талаас нь доорх дарааллаар үнэлэв. Үүнд: 1.Ерөнхий үнэлгээ буюу арга хэмжээний урт жагсаалт дээр матриц үнэлгээ хийх 2.Эрэмбэлэх үнэлгээ буюу салбарын мэргэжилтнүүдийн саналыг тусган, арга хэмжээнүүдий богино жагсаалт дээр олон шалгуурт шийдвэрийн шинжилгээ хийх 3.Сонгосон арга хэмжээг хэрэгжүүлэхэд гарах эдийн засаг, нийгэм, байгаль орчин, уур амьсгалын өртөг-өгөөжийн шинжилгээ /ӨӨШ/ хийх 4.GLEAM-i загварын тусламжтай сонгосон мал аж ахуйн арга хэмжээний төрөл, үйл ажиллагаанаас ялгарч болох ХХЯ –н тооцоог нарийвчлан тооцох Мал аж ахуйн салбарын уур амьсгалын өөрчлөлтөд ухаалгаар дасан зохицох нэгэн арга хэмжээ болох эр хургыг бэлчээрээр таргалуулан онд нь багтаан нядалж, хүнсэнд хэрэглэх нь эдийн засгийн төдийгүй байгаль орчин, уур амьсгалын 71 өөрчлөлтөнд дасан зохицох, сааруулах олон талын ач холбогдолтой байна.

According to the Center for Fire Statistics, there are about 50 million forest and steppe fires in the world each year. The periods from March 20 to June 10 and from September 20 to November 10 of each year in Mongolia are considered to be “Fire Hazard Periods” with dry weather conditions, favorable for forest and steppe fires. The analysis was done using Terra / MODIS satellite data during these months over the 2005-2020 years. The study area is Dornod province which has the highest events of forest and steppe fires in 2015. The events of forest and steppe fires have also increased since then and from the previous years. The study used satellite data and ArcGIS software to estimate modified soil-adjusted vegetation index, normalized difference vegetation index, and land surface temperature. Linear and nonlinear multi-factor regression analysis was applied to model the modified soil-adjusted vegetation index based on normalized difference vegetation index, land surface temperature, air temperature, wind speed, and precipitation for fire monitoring. The results show that the regression analysis, the modified soil-adjusted vegetation index in autumn depends on the factors such as normalized difference vegetation index, land surface temperature, air temperature, and precipitation, whereas land surface temperature, wind speed, and precipitation are the main factors in springtime. The output model’s coefficient of determination, which indicates the correctness of the regression equation ranges from 0.81 to 0.89

The vegetation is the most important factor of the biomass. It is also an important factor in cropland suitability and agriculture. In this paper, we aim to study vegetation, which related to several factors in steppe region. The study area is located in the northeast of Mongolia. The satellite data NDVI is commonly used for vegetation. In this study, we use the Normalized Difference Vegetation Index (NDVI) which depended on Land Surface Temperature (LST), The Normalized Difference Water Index (NDWI) from MODIS satellite data and Elevation, Slope from ASTER GDEM satellite data. This research focuses on two machine learning methods: Multiple linear and Random forest regression. We used MODIS and ASTER GDEM satellite data’s from 2001 to 2010 (July to August). The analysis was performed in Python Jupyter Notebook and ArcGIS. The result of both proposed models was compared with MODIS NDVI value. The validation results of these two methods are 71 and 91, respectively

This study investigates the spatiotemporal variations of Mongolian steppe and proposes a model for analyzing the relationship between grassland and biophysical parameters such as Land Surface Temperature (LST), Normalized Difference Water Index (NDWI), Elevation, and Slope. The Dornod province, which is one of the largest steppes in Mongolia, is selected as the study area, and data from 10 selected locations over this area during the growing season (April to September) from 2003 to 2018 are analyzed. The Normalized Difference Vegetation Index (NDVI) is used to characterize the grassland variations over the selected locations. NDVI and LST are obtained from Moderate Resolution Imaging Spectroradiometer (MODIS) data products. NDWI is estimated from MODIS spectral reflectance measurements. The Slope and Elevation are obtained from Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) Global Digital Elevation Model. A panel regression analysis method is applied to derive an empirical relationship between the grassland and the biophysical parameters. Statistical significance tests show that random effects model coefficients represent the relationships better. According to the results, NDWI has a strong positive dependence on NDVI, whereas the LST has a weak and inverse effect. Though the Slope had little effect, the Elevation showed a weak positive dependence. A validation of the model estimated NDVI with observations yielded a correlation coefficient of 0.83 at 5% significance level. The results suggest that the proposed model is suitable for for monitoring Mongolian steppe, and to examine the factors that contribute to the grassland variations.

Бутархай программчлалын минимумчлах бодлогыг бодохдоо шийдийг нь локаль шийдэнд хүргэдэг Dinkelbach алгоритмыг ашиглан зарим жишээ бодлого дээр туршилтуудыг хийв. Туршилтыг Dinkelbach алгоритмыг бутархай программчлалын шууд бодлоготой нь харьцуулах хэлбэрээр хийв. Энэхүү туршилтыг Python программ дээр ажиллуулав. Түлхүүр үгс: Бутархай программчлал, Dinkelbach алгоритм

Галын статистикийн төвийн гаргасан судалгааны дагуу дэлхийд жилд ойролцоогоор 50 гаруй сая ой, хээрийн гал түймрийн тохиолдол бүртгэгддэг. Монгол улсад жил бүрийн 3 дугаар сарын 20-ний өдрөөс 6 сарын 10-ний өдөр, 9 сарын 20-ний өдрөөс 11 сарын 10-ний өдөр хүртэлх хугацааг ой, хээрийн түймэр гарах байгалийн нөхцөл бүрддэг, хуурайшилт бүхий “Түймрийн аюултай үе” гэж үздэг. Эдгээр саруудын Terra/MODIS хиймэл дагуулын 2005-2020 оны мэдээнд тулгуурлаж шинжилгээ хийсэн. Судалгааны муж болох Дорнод аймагт 2015 онд ой, хээрийн түймэр хамгийн их буюу 71 удаагийн тохиолдол гарсан. Мөн тус оноос хойш ой, хээрийн түймрийн тохиолдол өмнөх онуудаас ихэссэн үзүүлэлттэй байна. Уг судалгааны ажлаар Хиймэл дагуулын мэдээг ARCGIS програмыг ашиглан хөрснөөс хамаарсан ургамлын индекс (MSAVI), ургамлын индекс (NDVI), газрын гадаргын температурыг (LST) тооцож гаргасан. Хөрснөөс хамаарсан ургамлын индексийг (MSAVI) ургамлын индекс (NDVI), газрын гадаргын температур (LST), агаарын температур, салхины хурд, хур тунадас зэргээс хамааруулан шугаман болон шугаман бус олон хүчин зүйлийн регрессийн шинжилгээ хийж загвар гаргасан бөгөөд эдгээр загвараа ашиглан бодит түймрийн мэдээлэлтэй харьцуулсан зураглал хийлээ. Регрессийн шинжилгээний үр дүнгээс харахад намрын улиралд хөрснөөс хамаарсан ургамлын индекс нь NDVI, LST, агаарын температур, хурд тунадас гэсэн хүчин зүйлсээс, харин хаврын улиралд LST, салхины хурд, хурд тунадас гэсэн хүчин зүйлсээс хамаарч байна. Эдгээр загварын хувьд регрессийн тэгшитгэлийн хир зөв сонгогдсоныг илтгэгч детерминацын коэффициент нь 0.81-0.89 хооронд гарч байгаа. Эдгээр үл хамаарах хувьсагчдын өөрчлөлтөөр хөрснөөс хамаарсан ургамлын индексийн өөрчлөлтийг 81-89% тайлбарлах боломжтой байна.

The Normalized Difference Vegetation Index (NDVI) is a graphical pixel indicator which used and analysed by remote sensing technology whether or not the target being observed contains live green vegetation. In this paper we estimated crop suitability using Normalized Difference Vegetation Index (NDVI) which depended on Land Surface Temperature (LST), The Normalized Difference Moisture Index (NDMI or water) from MODIS satellite data and Elevation, Slope form ASTER DEM satellite data. NDVI is used for several sector, especially in agriculture for cropland, precision farming and to measure biomass. Agriculture is one of the crucial and traditional sectors of Mongolia that produces approximately 15 % gross domestic production (GDP). This research focuses on estimation for crop suitability based on a statistical method and NDVI. The study area is situated in the steppe region Dornod province, eastern part of Mongolia. NDVI MODIS data (April to September) from 2003 to 2018 were applied for the estimation. We used multiple linear regression analysis with python in order to develop crop suitability model using NDVI. The result of proposed model was compared with MODIS NDVI value. The agreement is positive which 71percent.

Soil moisture is one of the essential variables of the water cycle, and plays a vital role in agriculture, water management, and land (drought) and vegetation cover change as well as climate change studies. The spatial distribution of soil moisture with high-resolution images in Mongolia has long been one of the essential issues in the remote sensing and agricultural community. In this research, we focused on the distribution of soil moisture and compared the monthly precipitation/temperature and crop yield from 2010 to 2020. In the present study, Soil Moisture Active Passive (SMAP) and Moderate Resolution Imaging Spectroradiometer (MODIS) data were used, including the MOD13A2 Normalized Difference Vegetation Index (NDVI), MOD11A2 Land Surface Temperature (LST), and precipitation/temperature monthly data from the Climate Research Unit (CRU) from 2010 to 2020 over Mongolia. Multiple linear regression methods have previously been used for soil moisture estimation, and in this study, the Autoregressive Integrated Moving Arima (ARIMA) model was used for soil moisture forecasting. The results show that the correlation was statistically significant between SM-MOD and soil moisture content (SMC) from the meteorological stations at different depths (p < 0.0001 at 0–20 cm and p < 0.005 at 0–50 cm). The correlation between SM-MOD and temperature, as represented by the correlation coefficient (r), was 0.80 and considered statistically significant (p < 0.0001). However, when SM-MOD was compared with the crop yield for each year (2010–2019), the correlation coefficient (r) was 0.84. The ARIMA (12, 1, 12) model was selected for the soil moisture time series analysis when predicting soil moisture from 2020 to 2025. The forecasting results are shown for the 95 percent confidence interval. The soil moisture estimation approach and model in our study can serve as a valuable tool for confident and convenient observations of agricultural drought for decision-makers and farmers in Mongolia.

It is very important for a company to determine spending for acquisition and retention of customers which affect the Customer lifetime value of the company. In this paper, we formulate the Customer lifetime value model as an optimal control problem. The obtained problem is to find an acquisition policy which maximizes the present value of all future profits generated from a customer. Here the state variable is the average margin for each customer about how much each customer contributes to the company and the control variable is the cost of acquisition. We use the maximum principle for optimality to solve the problem, estimate some parameters of the problem using statistical data for Mobile service sector of Mongolia and calculate the optimal customer life time values of the sector for some values of parameters.

We study an optimal control problem which is formulated to the classical growth theory. We assume that per capita capital is an increasing function and the saving rate is no longer constant and depends on time, then the average per capita consumption maximization problem reduces to an optimal control problem. The obtained problem has constraints imposed on trajectory as well as control. Hence, we apply the maximum principle for the problems with mixed inequality constraint to solve the problem. Some numerical results are included. We also show that the Solow growth model is a particular case of the proposed model.

Agriculture is one of the most critical sectors of the Mongolian economy. In Mongolia, land degradation is increasing in the cropland region, especially in a cultivated area. The country has challenges to identify new croplands with sufficient capacity for cultivation, especially for local decision-makers. GIS applications tremendously help science in making land assessments. This study was carried out in Bornuur soum, Mongolia. The goal of this study to estimate that best suitable area for supporting crop production in Bornuur soum, using a GIS-based multi-criteria analysis (MCA) and remote sensing. GIS-based multi-criteria analysis (MCA) has been widely used in land suitability analyses in many countries. In this research, the GIS-based spatial MCA among the Analytical Hierarchy Process (AHP) method has employed. The approach was enhanced for each criterion which as soil, topography and vegetation. The opinions of agronomist experts and a literature review helped in identifying criteria (soil data, topography, water and vegetation data) that are necessary to determine areas suitable for crops. The detailed cropland suitability maps indicate that 46.12 % is highly suitable for cropland, 34.68 % is moderate suitable, 13.64 % is marginal suitable and 5.56 % is not suitable. The MCA and AHP tools play an essential role in the multi-criteria analysis. Therefore, the results of these methods allow us to estimate an appropriate area for cultivation in Bornuur soum, Tuv province. The crop suitability method implies significant decisions on different levels and the result will be used for cropland management plan to make a decision. It is an integral role in agricultural management and land evaluation. Future research should further develop this method by including socio-economic (potential citizens for agriculture, current crop growth, water resource, etc.) and environmental variables (rainfall, vegetation types, permafrost distribution, etc.) to obtain specific results. However, it could be also be applied for a single crop type (mainly barley, wheat and potato) in Mongolia.

A study of the value of Mongolian forest resource in the shadow market KHULAN MYAGMAR1†, BAYANJARGAL DARKHIJAV2, ARIUNAA SHARANKHUU3 1,2,3Department of Applied Mathematics, National University of Mongolia, Baga toiruu Ulaanbaatar, Mongolia Email: khulan.m@seas.num.edu.mn ABSTRACT An approximately 8 percent of Mongolia's territory is covered by forests and which is largely distributed in the northern part of the country. The Mongolian forest resource is including forest resourse and non timber forest products which are berries, nuts, mushrooms, traditional medicinal herbs, herbs for food, raw materials, fuel wood, forage and game animals. The total forest resource is 124.35 million cubic meter, as well as 1.2 million cubic meter timber product is logged legally per year due to the statistics in the year 2017. In last two decays, the main policy of the forest sector has been largely controlled usage of forest resource, not based on demand of the wood and wooden products consumption. The impact of the policy has been improving the value of shadow market. The mongolian shadow market value is estimated 13 percent which is normal value. But If we look at the sector’s role of the whole economy, the value of the forest sector is seems to be high valued sector in the shadow market. There are 3 general methodoly which are direct, indirect and modeling methodology are used to estimate the value of shadow market in the research. In this paper, we used modeliing methodology to estimate that a pollution of timber production, and the value of illegal timber production. As a result, there is a pollution of timber production is estimated 5.8 times higher than the quantity of the timber production. Besides, the value of illegal timber production is estimated about 3 hundred million tugrugs between 2012 and 2016. According to the result of the study, we recommend that it is possible to increase an economic value of the forest sector to manage the policy. Keywords: Illegal timber production, shadow market, neo classic growth model

It is very important for a company to determine spending for acquisition and retention of customers. In this paper, we formulate the Customer lifetime value model as an optimal control problem. The obtained problem is to find an acquisition policy which maximizes the present value of all future profits generated from a customer. Here the state variable is the average margin for each customer which is how much each customer contributes to the company and the control variable is the cost of acquisition. We use the maximum principle for optimality to solve the problem, estimate some parameters of the problem using statistical data for Mobile service sector of Mongolia and calculate the optimal customer life time values of the sector for some values of parameters.

The Ulaan ereg is a branch of Ulz river which is located in the Pacific Ocean consists of taiga, forest steppe and steppe landscapes. The river basin is a suitable habitat for some animal species originated in Siberia, Mongolia and Manchurian and the endangered birds not only in Mongolia, but also in the world. Therefore, it is very important to protect the buffer zone along the Ulz River basin in order to save the endangered 4 species of the crane, 1 species of the goose and 1 species of the bustard. In this study we carried out cost-benefit analysis on the most suitable two scenarios that to create and protect the buffer zone which is located along with Ulz river. As results of the analysis indicate the most economically and environmentally beneficial one is Scenario1. Finally, risk assessment is made for NPV of Scenario-1.

The Ulaan ereg is a branch of the Ulz river which is located in the Pacific Ocean consists of taiga, forest steppe and steppe landscapes. The river basin is a suitable habitat area for some animal species originated in Siberia, Mongolia and Manchurian and the endangered birds not only in Mongolia, but also in the world. Therefore, it is very important to protect the buffer zone along Ulz River basin in order to save the endangered 4 species of the crane, 1 species of the goose and 1 species of the bustard. In this study we carried out cost-benefit analysis on the most suitable two scenarios that to create and protect the buffer zone which is located along with Ulz river. As results of the analysis indicate the most economically and environmentally beneficial one is Scenario1. Finally, risk assessment is made for NPV of Scenario-1.

Энэхүү ажилд хэрэглэгчийн өгөгдлийн сантай харилцах харьцааг хэрэглээний мэдээллийн системийн автоматжуулалт, програм, хөгжлийн асуудлыг шийдэх нэгэн аргын тухай авч үзсэн. Энэ асуудлыг шийдэх “Декларатив өвөрмөц тодорхойлолт”-од суурилсан мэдээллийн сангийн боловсруулалтын автоматжуулсан мэдээллийн системийг үүсгэх технологи, арга хэрэгслийн системийг боловсруулж, дэвшүүлсэн болно. Уг ажлаар дэвшүүлсэн арга нь өгөгдлийн сангийн загваруудыг судлах, боловсруулах тохиромжтой арга юм.