NUTS2 Level Research Articles

Transformation of the Organic Food Market in Poland Using Concentration and Dispersion

Purpose: This paper aims to isolate transformations that have been taking place on the Polish organic food market through the lens of cluster development with the intention to indicate the dynamics of organic food clusters – their concentration and dispersion. Design/Methodology/Approach: The employed methodology is centred around location quotient as a measure of concentration which allows to pinpoint clusters. The narrative in the paper follows the development of structures as the Polish organic food market undergoes various transitions. Findings: Organic farmland and organic operators in Poland are not evenly distributed regionally. The conducted study allowed the identification of development patterns of their regional concentration at NUTS-2 level. Throughout the analysed period certain regions have become specialised in organic farming and organic food processing. Practical Implications: As organic producers and organic food processors undergo a process of geographic concentration and are located in proximity with each other the clusters that are formed should translate into an increase of the competitive advantage of the supply-side of the Polish organic food market. Given the necessity to compete not only among each other but with conventional farmers and food processors as well as distributors, organic producers and organic food processors should make use of the proximity advantage and cooperate with the aim of strengthening their position on the market. Originality/Value: The authors undertook a study that goes beyond static analysis of the organic food market in Poland.

OK Computer: the creation and integration of AI in Europe

Abstract This article investigates the creation and integration of artificial intelligence (AI) patents in Europe. We create a panel of AI patents over time, mapping them into regions at the NUTS2 level. We then proceed by examining how AI is integrated into the knowledge space of each region. In particular, we find that those regions where AI is most embedded into the innovation landscape are also those where the number of AI patents is largest. This suggests that, to increase AI innovation, it may be necessary to integrate it with industrial development, a feature central to many recent AI-promoting policies.

A Model of Internal Migration: An Extended Neo-classical Migration Model and Evaluation of Regional Migration Determinants in Poland

The goal of this paper was to carry out an empirical verifi cation of the theoretical model of internal migration and evaluate the infl uence of selected determinants on internal migration in Poland. In order to achieve this goal, an analysis of internal migration in Poland and an econometric analysis were carried out. The analysis was processed using data from 16 voivodeships (i.e. on the NUTS2 level); the analyzed period was from 2003 to 2017. Based on selected theoretical concepts of migration and present studies on internal migration, the theoretical model of internal migration was specifi ed. A total of fi ve models were estimated; fi rst, four models were estimated for all voivodeships and subsequently a GLS estimate was carried out with the so-called “strong region”. Results of the econometric analysis show that regional wage differences together with differences in the unemployment rate determined internal migration, which is in agreement with the assumptions of neo-classical economy. The positive relationship was indicated between the degree of migration and its delayed variable last year, which points simultaneously to the validity of the assumption of the theory of cumulative causation. The test of the dummy variable has shown that the degree of regional migration increased in the period of crisis. From the perspective of push and pull factors, pull factors in the host region were the following determinants: wage, demand for work in the industrial sector of the economy, and foreign human capital; on the contrary, push factors included the increasing unemployment rate, housing costs and the degree of urbanization.

Analiza zróżnicowania rozwoju gospodarczego Regionu Stołecznego Litwy

Przedmiot badań: Przedmiotem niniejszego opracowania jest rozwój gospodarczy w samorządach Regionu Stołecznego Litwy. Jednym z motywów wyboru na obiekty badawcze ośmiu samorządów Regionu Stołecznego było utworzenie w 2016 r. dwóch nowych regionów na poziomie NUTS2, co miało zapobiec spadkowi środków pozyskiwanych z UE w nowym okresie finansowym, drugim – największą koncentracją w danych jednostkach terytorialnych mniejszości polskiej na Litwie.
 Cel badawczy: Celem artykułu jest określenie poziomu rozwoju gospodarczego w ośmiu samo­rządach Regionu Stołecznego Litwy oraz analiza porównawcza uzyskanych wyników.
 Metoda badawcza: W oparciu o przegląd literatury przedmiotu, który umożliwił wyjaśnienie pojęć wzrostu i rozwoju gospodarczego, jak również i danych statystycznych pochodzących z baz danych Departamentu Statystyki Litwy, zostały zbudowane syntetyczne mierniki metodami: Per­kala, Topsis i Hellwiga. Pozwoliły one na konstrukcję rankingów ośmiu samorządów Regionu Stołecznego według kryterium rozwoju gospodarczego w latach 2007, 2013 i 2018. Budowa ran­kingów w trzech latach motywuje się potrzebą zbadania zmian w uporządkowaniu samorządów. Do przeprowadzenia analizy wybrano początkowo 10 cech rozwoju gospodarczego, na których następnie dokonano weryfikacji zmiennościowej i korelacyjnej, stymulacji i normalizacji. W celu sprawdzenia jakości uzyskanych rankingów metodami Perkala, Topsis i Hellwiga obliczono współczynnik Sokołowskiego. W artykule zostały zaprezentowane rankingi w oparciu o miernik Hellwiga, gdyż charakteryzował się on największą zdolnością do grupowania samorządów.1
 Wyniki: Zastosowane metody badawcze pozwoliły stwierdzić, że Region Stołeczny charaktery­zuje się istotnym zróżnicowaniem rozwoju gospodarczego. Głównym wnioskiem artykułu jest konkluzja, że stworzenie w kraju nowych jednostek na poziomie NUTS2: Regionu Stołeczne­go i Regionu Litwy Środkowej i Zachodniej oraz możliwe ukierunkowanie większości środków unijnych w okresie 2021–2027 do Regionu Litwy Środkowej i Zachodniej może wywołać pogor­szenie sytuacji gospodarczej w najsłabszych samorządach Regionu Stołecznego oraz narastanie dysproporcji rozwojowych wewnątrz regionu.

To Make or to Serve – Industrial Specialization Drivers of Foreign Subsidiaries in Service and Manufacturing Sectors Across Agglomerations in a Transition Economy

This paper examines the dynamics of the location patterns of the foreign direct investment(FDI)subsidiaries in manufacturing and service sectors across regions in a developing economy before and after the accession of the European Union in 2004. The data at the NUTS level 2 on regions in Poland is analyzed employing the revealed location advantage (RLA) index for industrial specialization (RLAis) of the regions. The study tests the concentration patterns of industrial sectors along with the industrial specialization level of regions’ participating foreign enterprises across all regions of Poland. The findings allow answering for the presented hypothesis testing the level of industrial specialization across regions and its impact on narrowing industrial specialization, wages and the level of R&D investment. The results determine that the location of foreign firms in service-related industries is concentrating mostly in the largest agglomerations with the presence of large markets and universities. While, also, several regions seem to be able to narrow their manufacturing specializations, they generally locate at, or near, the legacy centers of those industrial sectors. This provides answers for, and confirms the raised hypothesis and generally follows the existing theoretical path of the developed economies. The study, also, shows that Polish regions attracting a higher number of foreign service-related investments also seem to increase their industrial specialization in select manufacturing sectors that can increasingly attract R&D investment.

Hungarian regions and cities towards an adaptive future – analysis of climate change strategies on different spatial levels

Nowadays, urban areas are increasingly identified as strategic fields of climate change-related actions. Climate change is an increasingly complex challenge for these territories. Tackling climate change, moreover, in a sustainable way, is a priority in the European Union, which has set several ambitious short- and long-term mitigation, adaptation, and sustainability targets. It is a central issue of how society can respond to the climate emergency that is affected by and depends on the vertical and horizontal interrelations among different stakeholders, organizations, governance actors, etc., and their activities. Countries, regions, counties, and cities around the world react by developing climate strategies. The operationalization of the high-level political agreements and discourses is uncertain, and the policies in practice should also be evaluated on regional and city levels, just as the milestones of related strategic planning processes fostering local adaptive capacity. According to regional and urban governance, it is pivotal addressing not only mitigation but adaptation issues to be able to foster sustainable regional development, also considering the UN Sustainable Development Goals (SDGs) specified in the Agenda 2030. Adaptation to climate change is increasingly becoming a priority for policy action. It also has high relevance to find the synergic interrelations towards an adaptive future. This paper evaluates the recent changes in Hungarian regional and urban planning in relation to climate policy approach and reports a state of adaptation oriented spatial planning on NUTS-3 (Nomenclature of Territorial Units for Statistics) and LAU-1 (Local Administrative Units) levels. The results are based on the collection of all relevant climate change-related strategic documents on these levels in Hungary and on the analysis of specific information. There is a lack of knowledge related to the comprehensive adaptation policy and planning on regional and local levels in Hungary. The results of the evaluation show the state-of-art knowledge related to possible adaptation pathways and the various engagement level for climate policy approach on different spatial levels in Hungary. In the case of the examined research area, the development of more mitigation oriented planning documents and low level of adaptation measures and monitoring process management tools is seen as critical.

СУБРЕГІОНАЛЬНИЙ РІВЕНЬ АДМІНІСТРАТИВНО-ТЕРИТОРІАЛЬНОЇ РЕФОРМИ В УКРАЇНІ: ДИСКУСІЙНІ АСПЕКТИ

Reforming the administrative and territorial structure of Ukraine within the process of decentralization has a number of unresolved issues. The second stage of the reform related to the formation of administrative and territorial units of the subregional level has now begun. The plan of 136 new districts approved by the Verkhovna Rada of Ukraine provoked a lively discussion both in the regions and in the expert community. The study analyses the approaches of scholars to the creation of administrative units of the subregional level in Ukraine in order to switch to a three-level model of territorial division. The article provides the arguments for and against the creation of new administrative and territorial units of the subregional level in Ukraine. The existence de facto in Ukraine of a number of inter-district territorial systems in various spheres – education, medicine, tax service – has been proved. Based on the analysis of quantitative criteria, written in the methodology for the creation of new districts, it was defined that they met the NUTS-3 level of the territorial division standard of the European Union countries. A comparative analysis of schemes for dividing the country into districts, which were developed by different Governments of Ukraine, and the network of districts approved by the Verkhovna Rada in 2020 was carried out. The article presents reasons for the increase in the number of new districts from 102 to 129 and then to 136 units, primarily due to the extension of their network in the temporarily occupied territories of Donbas and Crimea, as well as under pressure from regional representatives. The complexity of the issue of forming a network of new districts and their centres are described on the example of Chernihiv region. It is determined that the average population of the project district in Ukraine is 303 thousand people, the population of the centre of administrative units of the subregional level, 130 thousand people. The significant disparities (from 58 to 362 times) in the population of new districts and their centres were defined. Based on the calculations, it was found that 26,5 % of new districts have less population than that determined by the methodology of forming administrative units of the subregional level (150 thousand people). The situation with the population of district centres is similar. Almost 50 % of subregional centres approved by the Verkhovna Rada of Ukraine account for less than 50 thousand people, which may be an obstacle to form high-quality human resources of the executive bodies. It is defined that the competition between cities for the status of the new district centre is due to the desire of local elites to retain control over certain areas. The ambiguous attitude to the issue of creating administrative units of the subregional level on ethnic grounds (Bolhrad and Berehovo districts) among experts and regional elites is pointed out. The list of personnel, financial, property issues that need to be resolved in order to build an effective executive branch in Ukraine at the subregional level has been determined.

Regional household poverty and mobility analysis – a transition probability approach

The main objective of this paper was to estimate and analyse transition-probability matrices for all 16 of Poland’s NUTS-2 level regions (voivodeship level). The analysis is conducted in terms of the transitions among six expenditure classes (per capita and per equivalent unit), focusing on poverty classes. The period of analysis was two years: 2015 and 2016. The basic aim was to identify both those regions in which the probability of staying in poverty was the highest and the general level of mobility among expenditure classes. The study uses a two-year panel sub-sample of unidentified unit data from the Central Statistical Office (CSO), specifically the data concerning household budget surveys. To account for differences in household size and demographic structure, the study used expenditures per capita and expenditures per equivalent unit simultaneously. To estimate the elements of the transition matrices, a classic maximum-likelihood estimator was used. The analysis used Shorrocks’ and Bartholomew’s mobility indices to assess the general mobility level and the Gini index to assess the inequality level. The results show that the one-year probability of staying in the same poverty class varies among regions and is lower for expenditures per equivalent units. The highest probabilities were identified in Podkarpackie (expenditures per capita) and Opolskie (expenditures per equivalent unit), and the lowest probabilities in Kujawsko-Pomorskie (expenditures per capita) and Małopolskie (expenditures per equivalent unit). The highest level of general mobility was noted in Małopolskie, for both categories of expenditures.

General Patterns and Drivers of Changes in Employment Structure: Evidence from Five European Countries

This paper seeks to answer whether the general patterns and drivers of the sectoral employment shifts depend on a country’s level of development. To accomplish this, we examined employment in Germany, Hungary, Poland, Romania and Ukraine at the national level (1998-2018) using econometric analysis, and at the regional NUTS2 level (2009-2018) using shift-share analysis. We obtained evidence that the general trend is the service sector expansion. Using the ARDL approach and the Granger causality test, we identified long-run unidirectional causality running from income proxies to employment in services in all countries except Romania, where the opposite causality was found. We revealed that household income moderates the impact of urbanization on service sector growth in all countries except Poland. At the regional level, the change in the employment rate in services is explained by the national growth effect and slightly by the industry-mix effect if the active phase of structural changes is completed.

Aspects of the Development of Lithuanian Economic Specialisation in the Context of Globalization

Aspects of the Development of Lithuanian Economic Specialisation in the Context of Globalization

Analysis of relationship between cereal yield and NDVI for selected regions of Central Europe based on MODIS satellite data

Earth observation satellite technologies allow the status of crops to be assessed at various geographical scales. The most popular vegetation index for analyzing this status is the Normalized Difference Vegetation Index (NDVI). This article studies the relationship between the NDVI and cereal-grain yield in selected regions (corresponding to NUTS2 levels) of four Central European countries: Poland, Germany, the Czech Republic, and Slovakia. The remote sensing data cover the vegetation seasons (from the beginning of March until the end of June) of 2012–2016, and were obtained using the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor of NASA's Terra satellite. The average NDVI of the data was calculated for both the entire area and the arable-land area of the regions (according to the Corine Land Cover program). Statistical analysis includes correlation and linear regression analyses between cereal grain yield and mean NDVI for entire area and arable land of the regions in each year of the study. They are strongly correlated from the beginning of March until mid-May (most of the correlation coefficients for arable land are between 0.50 and 0.85), the strongest relationship being around the beginning of April in the Czech Republic and Slovakia (most of the correlation coefficients are between 0.80 and 1.00). In most regions of Poland, the relationships are quite strong, but in German regions they are weak and inconsistent. Regression coefficients (slopes) for relationships between the NDVI in the beginning of April and the grain yield of cereals range from 10.8 to 26.2. This means that an increase in the NDVI in early spring by 0.1 unit increases the grain yield of cereals by about 1.1–2.6 t/ha. The obtained results are promising because they prove the possibility of forecasting cereal grain yield at the regional level, three–four months before the harvest, which is important for planning food policy.

Latin American consumption of major food groups: Results from the ELANS study.

BackgroundThe Latin American (LA) region is still facing an ongoing epidemiological transition and shows a complex public health scenario regarding non-communicable diseases (NCDs). A healthy diet and consumption of specific food groups may decrease the risk of NCDs, however there is a lack of dietary intake data in LA countries.ObjectiveProvide updated data on the dietary intake of key science-based selected food groups related to NCDs risk in LA countries.DesignELANS (Latin American Study of Nutrition and Health) is a multicenter cross-sectional study assessing food consumption from an urban sample between15 to 65 years old from 8 LA countries (Argentina, Brazil, Chile, Colombia, Costa Rica, Ecuador, Peru, and Venezuela). Two 24-HR were obtained from 9,218 individuals. The daily intake of 10 food groups related to NCDs risk (fruits; vegetables; legumes/beans; nuts and seeds; whole grains products; fish and seafood; yogurt; red meat; processed meats; sugar-sweetened beverages (ready-to-drink and homemade)) were assessed and compared to global recommendations.ResultsOnly 7.2% of the overall sample reached WHO’s recommendation for fruits and vegetables consumption (400 grams per day). Regarding the dietary patterns related to a reduced risk of NCDs, among the overall sample legumes and fruits were the food groups with closer intake to the recommendation, although much lower than expected (13.1% and 11.5%, respectively). Less than 3.5% of the sample met the optimal consumption level of vegetables, nuts, whole grains, fish and yogurt. Largest country-dependent differences in average daily consumption were found for legumes, nuts, fish, and yogurt. Mean consumption of SSB showed large differences between countries.ConclusionDiet intake quality is deficient for nutrient-dense food groups, suggesting a higher risk for NCDs in the urban LA region in upcoming decades. These data provide relevant and up-to-date information to take urgent public health actions to improve consumption of critically foods in order to prevent NCDs.

Specialisation Vs Diversification. Which One Better Upholds Regional Resilience to Economic Crises?

Abstract As economic crises periodically disrupt the economic activity, a large and continuously growing literature was dedicated to understanding the reasons behind the crises, their mechanism, effects and, most of all, the determinants of resilience capacity, and the ability to overcome hardships by adapting and changing. By preparing in advance for economic shocks through resilience building during good times, the impact of economic crises can be attenuated. Starting from these considerations, the paper focuses on regional economic specialization and its opposite – economic diversification, two business strategies already acknowledged in the literature as relevant factors for the capacity to mitigate economic crises. We tested the hypothesis of vulnerability-inducing economic specialization in the Romanian economy, using NUTS3 level data and found that more diversified regional economies were better at coping with the hardships triggered by the recent recession.

A Spatial Econometric Analysis of Health in Romania Augmented with Computer Vision

Abstract The purpose of this study is to analyze the health status in Romania at regional NUTS3 level together with its influential socio-economic factors. Apart from statistical and classical econometrics which are being used in most studies, a spatial analysis has been conducted in order to determine possible similarities and dissimilarities among regions, accounting for the fact that events taking place in a specific area are interrelated with the events in the neighboring regions. The negative distribution of the dependent variable, life expectancy, involves the use of Quantile Spatial Autoregressive Model which also allows to observe the socio-economic and environmental factor influences in different parts of health status proxy distribution. The analysis has led to the conclusion that greater the gaps between rich and poor, or greater the difference between less versus better educated, the greater the differences in health status and life expectancy are. Hence a need for policies designed to reduce territorial health disparities has been identified across Romania’s counties. Moreover, Computer Vision and Deep Learning techniques have been used in order to showcase data collection for urban green spaces variables given that more than half of the globe population is living in urban areas and urban greenery has a high positive influence on health. Using Deep Learning on this particular matter together with the Quantile Spatial Autoregressive Model is an innovative approach that has the main aim of improving the classical econometric modelling.

Determination of individuals’ life satisfaction levels living in Turkey by FMCDM methods

Purpose This study aims to determine the ranking of the 81 provinces at the NUTS-3 level in Turkey with respect to the personal satisfaction and public services satisfaction by applying Fuzzy Multi-Criteria Decision-Making methods to the Life Satisfaction Survey Results. Design/methodology/approach Fuzzy TOPSIS, Fuzzy MULTIMOORA and Fuzzy ARAS are implemented to assess life satisfaction of the individuals who lived in provinces, based on Life Satisfaction Survey 2013 for Turkey’s national comparison. In the solution process, 14 indicators for personal satisfaction and 38 indicators for public services satisfaction were considered. Findings The results showed that personal health satisfaction, earnings from work satisfaction and monthly income satisfaction are the most important criteria in terms of personal satisfaction. Also, healthcare services satisfaction, judicial services satisfaction and education services satisfaction have the highest importance in terms of public services satisfaction. The final ranking of the 81 provinces is obtained by considered methods. According to the ranking results, there is no significant difference between the east and the west part of Turkey in terms of personal satisfaction, whereas there is a distinct difference between them in terms of satisfaction with public services. Originality/value This study is the first research for evaluating the ranking of the provinces at the NUTS-3 level in Turkey according to the Life Satisfaction Survey 2013 results considering 14 indicators for personal satisfaction and 38 indicators for public services satisfaction by using FMCDM approaches that have not been applied before.

Beyond GDP: an analysis of the socio-economic diversity of European regions

ABSTRACTThis paper aims to analyze the socioeconomic diversity of the European Union (EU-28) regions from a dynamic perspective. For that purpose, we combine a series of exploratory space-time analysis approaches to multiple Factor Analysis (MFA) applied to a large range of indicators collected at the NUTS-2 level for the period 2000–2015 for the EU-28. First, we find that the first factor of MFA, interpreted as economic development (ECO-DEV), is spatially clustered and that a moderate convergence process is at work between European regions from 2000 to 2015. Second, when comparing these results with those obtained for Gross Domestic Product (GDP) per capita, we show that the convergence pattern detected with GDP per capita is more pronounced: ECO-DEV adjusts slower over time compared to GDP per capita. Third, pictures provided by the remaining interesting factors, capturing educational attainment, population dynamics and employment, are very different.

Challenges and solutions in identifying agricultural pollution hotspots using gross nitrogen balances

Gross nitrogen balances (GNB) at the national level are a broad indicator of reactive nitrogen (N) pollution but the identification of pollution hotspots is necessary for designing cost-effective abatement policies. This requires a spatial disaggregation of GNBs to finer resolutions, but key inputs are often only available at high spatial scales. Modelling offers a method to provide these inputs but introduces additional error. Here we develop methods to estimate the main inputs (manure, synthetic fertiliser) and outputs (roughage feed and crop products) for mainland Portugal for the NUTS2, NUTS3 and municipality levels for the years 1989, 1999 and 2009. Our results show that despite the declining of the mainland GNBs over this period (47 to 38 kg N ha-1),the range of GNBs at progressively finer resolutions increased from 26 to 95 at the NUTS3 to −50–963 kg N ha−1 at the municipality levels. The increased concentration of livestock in some areas appears to be leading to an inefficient use of manure for crop production whereas there appears to be a depletion of soil N stocks in other areas. A comparison of our results with those from Denmark leads us to conclude that themunicipality level is the most suitable to identify hotspots, even thougherrors can arise when there is a poor correspondence between agrienvironmental conditions and the socioeconomic administrative boundaries at which statistical data are often available.

A comparison of remotely-sensed and inventory datasets for burned area in Mediterranean Europe

Quantitative estimate of observational uncertainty is an essential ingredient to correctly interpret changes in climatic and environmental variables such as wildfires. In this work we compare four state-of-the-art satellite fire products with the gridded, ground-based EFFIS dataset for Mediterranean Europe and analyse their statistical differences. The data are compared for spatial and temporal similarities at different aggregations to identify a spatial scale at which most of the observations provide equivalent results. The results of the analysis indicate that the datasets show high temporal correlation with each other (0.5/0.6) when aggregating the data at resolution of at least 1.0° or at NUTS3 level. However, burned area estimates vary widely between datasets. Filtering out satellite fires located on urban and crop land cover classes greatly improves the agreement with EFFIS data. Finally, in spite of the differences found in the area estimates, the spatial pattern is similar for all the datasets, with spatial correlation increasing as the resolution decreases. Also, the general reasonable agreement between satellite products builds confidence in using these datasets and in particular the most-recent developed dataset, FireCCI51, shows the best agreement with EFFIS overall. As a result, the main conclusion of the study is that users should carefully consider the limitations of the satellite fire estimates currently available, as their uncertainties cannot be neglected in the overall uncertainty estimate/cascade that should accompany global or regional change studies and that removing fires on human-dominated land areas is key to analyze forest fires estimation from satellite products.

An analysis to detect exuberance and implosion in regional house prices in Turkey

The aim of this paper is to find out whether there is exuberance in regional house prices in Turkey. For this purpose, we analyze real hedonic house prices and price to rent ratios countrywide as well as for 26 geographic regions at the NUTS2 level from January 2010 to January 2019. We perform the right-tailed unit root testing procedures developed by Phillips et al. (2015) and Phillips and Shi (2018) and use their real time date-stamping strategy to determine periods of explosiveness and implosion. Our empirical findings indicate that there were exuberance episodes in house prices in Turkey for multiple periods, where an important contributor to these dynamics was the largest housing market, İstanbul. We also detect exuberance in some other regions, particularly in the neighboring NUTS2 regions of İstanbul and in İzmir after around 2014. However, we find out that explosive price behavior turned into implosion in many regions starting from 2018.

Modeling electricity consumption using nighttime light images and artificial neural networks

The purpose of this paper is to model electricity consumption using Artificial Neural Networks (ANN). Total electricity consumption and consumption generated by households (HH) were modeled. The input variables of the ANN were based on nighttime light images from VIIRS DNB. Studies conducted thus far have covered mainly linear models. Most of case studies focused on single countries or groups of countries with only few focusing on the sub-national scale. This paper is pioneering in covering an area of Poland (Central Europe) at NUTS-2 level. The use of ANN enabled the modeling of the non-linear relations associated with the complex structure of electricity demand. Satellite data were collected for the period 2013–2016, and included images with improved quality (inter alia higher resolution), compared to the DMSP/OLS program. As images are available from April 2012 onwards, it is only recently that their number has become sufficient for ANN learning. The images were used to create models of multilayer perceptrons. The results achieved by ANN were compared with the results obtained using linear regressions. Studies have confirmed that electricity consumption can be determined with higher precision by the ANN method.