Climate change is one of the common problems in today’s societies AND considerate as threat for earth. Increasing of earth temperature is cased to extensive changes in earth climates AND also it laded to same variations of spatial AND temporal of PRECIPITATION so that these variations cased to a lot of damages especially in last decade. This study to identify of variations AND the trEND of season AND duration of PRECIPITATION in different times intervals. Then it is predicted same changes in the future by the method of artificial neural network. In this study we have us of the data from two synoptic stations Hamadan AND Nojeh. The statistic’s years in this study, it seems the rainfall season in the central part of Hamadan province in STARTed later AND ENDed later in last decade. In other words the STARTer of rainfall season in Hamadan which occurred in the fall season, at present tEND toward the winter season AND the fall season is more dryer than before ages. This shows that the rainfall season is interchanged in this district. in using of the method of artificial neural network we should consider to two main points in the predicting of PRECIPITATION the first one, the low attention of this method in the long –term predicting of PRECIPITATION AND the second one, the exaggerate in the minimum AND maximum amount of PRECIPITATION in different seasons of year.

Frost refers to conditions in which the air temperature reaches zero or zero degrees Celsius at an altitude of about one to two meters from the ground. Almost every part of the economy may be affected by unexpected frostbite AND in most cases, freezing occurs negatively. Freezing temperatures are zero or less than zero. The term "frost" means that the temperature is zero or less than that in a given region. Because of the importance AND application of forecast freezing AND regional economic development planning Attempts were made to investigate the changes AND the beginning AND END of the ice in the western regions of Iran during a twenty-year period, using the general data of the atmospheric circulation data AND its changes.

Introduction One of the climatic factors that occur during the cold period of the year in most parts of the country is the phenomenon of cold AND glacial. Glacial begins when the temperature decreases AND falls to a certain critical threshold, AND with the effects it has on the earth's surface, it affects human life as well as construction activities AND the yield of horticultural crops. This complication occurs on fruit trees in winter or early spring AND causes a lot of damage. The glacial phenomenon not only ENDangers the natural life of all living things but also plays an important AND decisive role in economic, environmental, AND development matters such as roads, dams, AND bridges. Glacial is very important in different stages of growth of agricultural AND horticultural crops. Because if happen, it leads to production constraints. Glacial means zero temperatures or less than zero. Likewise in terms of technology for agriculture, in the event of thin ice crystals formation on the surfaces with sub-zero temperatures, the temperature of the surface air layer is reached above the dew point. In terms of farming meteorology, glacial is related to the low-temperature alteration which causes damage to the tissues of the plant. Glacials can be classified based on the severity, duration, AND timing of occurrence. The classification based on the severity is the power of energy distribution components, which usually are measured based on average temperature, minimum, AND average of zero AND sub-zero AND the lowest temperature of the minimums. The beginning AND END dates of the glacial period are important from an agricultural point of view. The first glacial that occurs at the beginning of the glacial age is called early autumn glacial. In the autumn, glacial earlier than normal damage to actively growing branches. The last glacial that occurs at the END of the glacial period is called the late spring glacial. Fruit trees are increasingly susceptible to glacial damage from the time flower buds open, during flowering to the stage of small green fruit. To minimize glacial damage in susceptible areas, full knowledge of the frequency, persistence, AND timing of glacial events is essential. To measure the risk of glacial, the recorded data of the minimum air temperature in meteorological stations are used. From a meteorological point of view, glacial occurs when the surface temperature AND vegetation on it decrease to less than zero degrees Celsius. Materials AND Methods In the current study, the minimum daily temperature statistics of 10 meteorological stations during a period of 17 years (2001-2018) have been used. To analyze the frequency of glacial occurrences for each year, the time of occurrence of the first early autumn glacial AND the last late spring glacial was obtained. To convert the data into processable numbers based on the Julian days, each date is assigned a number. Based on this, the September 23 (1st of Mehr) was considered No. 1 AND August 23 (31st of Shahrivar) in normal crop years was considered 365, AND based on this, the number of the first glacial (early autumn cold) AND the last glacial (late spring cold) were identified separately based on the stations during each crop year. Days, when the temperature was less than zero degrees Celsius, were extracted as glacial day AND glacial at 5 weak temperature thresholds (temperature between zero to -1.9 degrees Celsius), mild (temperature between -1.9 to -3.9 ° C), moderate (temperature -4 to -5.9 ° C), severe (temperature between -6 to -9.9 ° C) AND very severe (temperature -10 ° C AND Less) was studied (adapted from Qalehri, 2018: 16). Using SPSS software, the best statistical sequence was obtained to calculate the START AND END dates of glacial at different probability levels. The results indicated that most of the selected statistical series have a normal distribution. ArcGIS software was used to zoning the time of onset AND END of glacial AND to prepare many maps of glacial occurrence. Result AND discussion The spatial distribution of the beginning of the glacial in the province follows the topographic state of the region AND begins earlier in the southern AND southeastern parts of the province. In some parts of the southern AND southeastern regions, due to the high altitude of the region AND being located in the mountainous areas, early autumn glacial occurs earlier, such as Garizat station, AND occurs from November 6 to 12 (Aban 15 to 21). At Bafgh station, the beginning of autumn glacial occurs from November 13 to 19 (Aban 22 to 28). At Marvast, Meybod, AND Abarkooh stations, the STARTing date of glacial is from November 20 to 25 (Aban 29 to Azar 4). The date of occurrence of early autumn glacial in Herat AND Robat stations is November 26 to December 2 (5 to 11 Azar). The beginning date of glacial in Mehriz, Yazd, AND Aqda stations is from December 3 to 9 (12-18 Azar). The beginning date of glacial based on different probabilities in Garizat stations with a probability of 30%, is November 3 (12 Aban), with a probability of 50% is November 6 (15 Aban), with a probability of 70%, November 9 (18 Aban), AND with a probability of 90%, November 14 (Aban 23), as the earliest START date of autumn glacial. At Yazd station, with a probability of 30%, the first glacial has occurred on November 23 (2 Azar), with a probability of 50%, December 4 (Azar 13), with a probability of 70%, December 8 (Azar 17) AND with a probability of 90% on December 24[Ma1]  (3 Dey). The glacial at Bafgh station will END sooner on January 8 -17 (18-27 Bahman). Glacial in central AND southern areas such as Mehriz, Yazd, Aqda, AND Herat will END on February 18 to February 26 (Bahman 28 to EsfAND 7). At Meybod, Abarkooh, AND Robat Posht Badam stations, the END date of the glacial is February 27 to March 9 (EsfAND 8-18). At Marvast station, the END of the glacial occurred on March 9-19 (EsfAND 18-28). In the highlANDs, including Garizat station, the glacial STARTs earlier AND ENDs later, so the glacial season is longer in these areas AND the growing season is shorter, March 20-30 (EsfAND 29 to Farvardin 10). The END date of glacial at Bafgh station with a probability of 30%, occurs at January 23 (Bahman 3), with a probability of 50%, February 12 (Bahman 23), with a probability of 70%, February 25 (EsfAND 6) AND with a probability of 90%, March 5 (EsfAND 14). At Garizat station, the last glacial occurs with a probability of 30% on March 26, (Farvardin 6), with a probability of 50%, on March 29 (Farvardin 9), with a probability of 70% on March 31 (Farvardin 11), AND with a probability of 90% on April 8 (Farvardin 19). The spatial distribution of the number of glacial days on the threshold zero shows that southeast areas including Garizat station have the most frosty days (1685 days) AND Bafgh (483 days), Mehriz (484 days), Robate Posht Badam (518 days), Yazd (463 days) AND Aqda (362 days) have the lowest number of glacial days during the statistical period (2001-2018). Spatial distribution of glacial occurrence at temperature thresholds of (0 AND -1.9) have the highest number of glacials AND the central AND northern regions have the lowest number of glacials. Therefore, the Garizat station (467 days) has the highest amount of glacial, AND Bafgh AND Aqda stations have the lowest amount of glacial at this threshold. Likewise, on the threshold (-2 to -3.9), the southeastern AND northwestern regions have the highest number of glacial AND the northern AND central regions have the lowest number of glacial. So, Garizat, Abarkooh, AND Meybod stations have the highest amount of glacial AND Mehriz, Yazd, Bafgh, Robat-e Posht Badam AND Aqda stations have the lowest amount of glacial at this threshold. Conclusion Studies conducted between the START AND END dates of glacial AND the height of selected stations showed that there is a significant relationship between altitude AND the date of occurrence of early autumn glacials. As altitude increases, glacial begins sooner. This fact designates that early autumn glacials happen earlier in the mountains than in the plains. The glacial onset map shows that in the plains of the province, the time of the first glacial is about a month later than the highlANDs of the province. In late spring glacials, the relationship between altitude AND the END of the glacial is direct AND by increasing the altitude, the date of the last spring glacial is delayed. This indicates that in the plains, the glacial period begins later AND ENDs earlier, in other words, the glacial season in these areas is shorter AND the growing season is longer. Conversely, in the highlANDs, the length of the glacial increases, AND the length of growth decreases. This is significant from an agricultural point of view. Besides, the frequency of glacial in the southern AND southeastern regions is higher than in the northern AND northeastern regions, which has a significant relationship with altitude. The results of the analyzes showed that the Garizat station has the most glacial at all thresholds in the studied period. The lowest amount of glacial days is related to Bafgh, Aqda, AND Mehriz stations in the temperature threshold (less than -10). The spatial distribution of the occurrence of glacial at different temperature thresholds also showed that in general, the southern AND southeastern regions of the province have the highest frequency of this phenomenon, AND as we move to the north of the province, the frequency of glacial decreases.

Purpose: Resilience in START-ups is a challenging issue that has caught the attention of policymakers AND business owners. The present study is an attempt to provide a model for designing the resilience model of START-up businesses as a path to the future of START-up businesses. Method: This research is practical in terms of purpose AND from the perspective of data collection is a qualitative research that has been done by content analysis method. The data collection method is semi-structured interview. Interviews with participants continued until they reached the theoretical saturation point, which was achieved by conducting 15 interviews. Participants were selected by snowball AND purposeful method AND data analysis was done through three coding steps (open, axial, selective) with MAXQDA2020 software. Findings: Based on the research results, the components of "cognitive resilience, financial resilience, adaptive resilience" as well as the effective organizational factors of "precedent, drivers AND boys AND resilience consequences" were identified. In this research, foresight AND futures studies were identified as the drivers of resilience of START-up businesses. Conclusion: Resilience enables businesses to respond effectively to the dynamic conditions of their environment AND maximize their competencies through strategic foresight AND as a result gain more value than their competitors in the field of business. In this regard, the integration of foresight in the process of business resilience can be suggested as a facilitator of drivers.

One of the most important main indicators in the performance criteria of self-driving cars is the policy adopted by the self-driving system regarding the determination of vehicle speed AND steering angle. To determine this policy, researchers have always faced the challenge of choosing our optimal training method between two traditional modular AND modern END-to-END approaches. Recently, a lot of research has been done in order to introduce the END-to-END approach AND its application in this field. In this research, an optimal model for predicting the driver's behavior has been presented using this modern approach in the form of deep learning for training artificial neural networks. In other words, achieving a model with acceptable accuracy compared to similar tasks in driving a self-driving car has been considered. For this purpose, based on the investigations carried out on the architecture of the existing networks, two architectures that have the necessary potential to achieve this goal were selected. Also, in order not to ignore the time relationship between the slides to show the visual time depENDencies, AND to check its effect on the result, the combination of convolutional neural networks (convolutional) with a type of recurrent network called long short-term memory LSTM was used in the training of the model. Also, a complete data set collected in real driving conditions AND labeled including images AND depth information has been used, AND by designing training algorithms AND optimizing training parameters using the Adam optimization algorithm Several trained models were presented. Among the obtained results, some predictions were more optimal than similar works, which shows the unique effect of temporal depENDencies in the training AND effectiveness of recurrent networks along with the strong processing of convolutional networks.

Iranian painting has always appeared in the form of manuscripts. Manuscripts have been admitted to provide artists with the work of coordinating AND linking between writing AND graphic art AND empty spaces, to reach a beautiful AND balanced layout of interest to artists. This article attempts to study the evolution of book publishing practices AND has a fresh look at the layout of Iranian manuscripts from the Seljuk period to the END of the Safavid period. In this research, the documentary study AND content analysis method are used to study the layout patterns in the manuscripts used as the data of the study. Each manuscript in Iran has several sections that include text pages, text AND image pages, image pages, page lists, END page, header page, START pages. Each of these sections, alone or in conjunction with other sections, has visually specific visual methods for aligning elements AND adjoining components AND components. The principles of page composition in each of the categories mentioned above have evolved over time, influenced by the artistic principle of the time. This article deals with various sections of a version that explores the beginning AND ENDing pages over time. Investigating AND analyzing the samples showed that clear AND regular principles in the Iranian manuscripts page layout in the periods mentioned above, which can be extracted AND modeled AND used, can be recharged into the page layout of today's Books. The results show that the form of the composition of the header pages is influenced by the START page AND their formation can be related to the beginning pages. The simpler header pages were commonly used during first Islamic centuries in Iran, but later on the designs AND layouts in these pages ranges AND became more complicated. it should be mentioned that the header was first used in order to write the section names in literary books. In Quran the header contains one word mostly the attributes of god. The use of simple sentences in the header parts makes the change in the form of the header in pages. So, these changes led to the use of two different pages in book designing: header page AND the START page. The START pages remain simple in design until the Jalayeries era. Most of the START pages do not have ant texts although in later times the attributes of God were used in the START pages of a few of book. After the Safavid era, the START pages were completely illustrated by arabesques AND other ornaments. Completely designed AND colored in bright AND shining colors. During the Safavid era it is the ornamentation which matters AND layout of the page obeyed the ordinary types of the time. The header pages are also simple in first Islamic centuries. From Ilkhanid to Safavid the round shapes or ornaments were common in header pages. The simple palmetto or floral motifs beside the geometric patterns were common. Although during the Timurids the header pages became a common part of the books which were designed by Islamic motifs in books but is just during the safavids that the complicated designs were used in the header pages.

In order to monitor spatiotemporal variability of snow in mountainous areas such as Zagros in Iran, long-term records of snow observations with high spatial resolution are required. However, no such data are either observed or available for the stations of the Zagros region. Therefore, in this study, the Era-Interim/LAND snow depth data for the period 1979-2010 were used in order to investigate the spatiotemporal variability of snow season length AND the associated STARTing AND ENDing dates in the Zagros region. To do so, for each hydrological year STARTing from October AND ENDing in September, the first AND last snow dates with snow depth equal to or greater than one centimeter were defined as the first AND last day of observed snow on the ground AND the time period between these two dates was considered as the snow season length. For each grid points over the study area, the time series of snow START AND END dates, as well as the length of the snow season, were extracted AND the rate of their temporal changes was estimated using the Sen Slope estimator AND were examined using the Mann-KENDal trEND test to test if they are statistically significant. Moreover, the considered time period was divided into three different sub-periods AND the mean values of these parameters (i. e., first AND last snow dates AND snow season length) in the three sub-periods were also compared. The links between these parameters AND the latitude, longitude, AND altitude of the grid points were also examined. Results indicated that the spatial pattern of the first AND last snow dates AND snow season length fairly follow the geographical features of the study area AND thus have a statistically significant relationship with the latitude, longitude, AND altitude. Time variability of the considered parameters over all the studied grid points revealed that the date of the first snow in the most proportion of the study area retreated towards the late autumn AND January AND the date of the last snow also retreated towards March AND February, thus, resulting in the shorter winter season in recent years. The observed statistically significant decreasing trEND in the time series of the last snow dates towards March AND February has the most contribution in shortening the length of the snow season.

Introduction: Humans AND plants can grow in a certain temperature range AND shall bear their ability against the high AND low temperatures are limited. Decrease temperature of minimum thresholds of plants AND occurrence of frost damage on roads every year the vast country’s economy will enter. Study the tempo-spatial distribution of frost occurrence is the most fundamental climate research, which can planners to reduce cold AND frost damage to guide AND assist (Kamali, 151:2002).Many studies in Iran AND the world about this phenomenon have been done. The most important studies in other countries can be Suckling Studies (1988), in the southeastern United States, Watkins (1991) in the UK, Eriksson AND Lindquist (2002) noted in Sweden.