پديد آورندگان :
محمودزاده، حميد دانشگاه لرستان - گروه علوم خاك , متين فر، حميد رضا دانشگاه لرستان - گروه علوم خاك , تقي زاده مهرجردي، روح الله دانشگاه اردكان - گروه علوم كشاورزي و منابع طبيعي
كليدواژه :
داده كاوي , نقشه برداري ديجيتال خاك , پهنه بندي كربن آلي خاك , شهرستان كامياران
چكيده فارسي :
ﺳﺎﺑﻘﻪ و ﻫﺪف: ﮐﺮﺑﻦ آﻟﯽ از ﻃﺮﯾﻖ ﻧﮕﻬﺪاﺷﺖ ﺑﺨﺶ ﻗﺎﺑﻞ ﺗﻮﺟﻬﯽ از ﻓﺮمﻫﺎي آﻟﯽ ﻗﺎﺑﻞ ﻣﻌﺪﻧﯽﺷﺪن آن در ﺧﺎك، ﻧﻘﺸﯽ ﺣﯿﺎﺗﯽ در ﮐﻨﺘﺮل اﻗﻠﯿﻢ و ﭘﺎﯾﺪاري ﻣﺤﯿﻂ زﯾﺴﺖ دارد. ﻫﻢ ﭼﻨﯿﻦ ﮐﺮﺑﻦ آﻟﯽ ﺗﺄﺛﯿﺮ ﮐﻠﯿﺪي ﺑﺮ ﺧﺼﻮﺻﯿﺎت ﻓﯿﺰﯾﮑﻮﺷﯿﻤﯿﺎﯾﯽ و ﺑﯿﻮﻟﻮژﯾﮑﯽ ﺧﺎك دارد؛ ﺑﻪ ﻧﺤﻮي ﮐﻪ از آن ﺑﻪ ﻋﻨﻮان ﺷﺎﺧﺺ ﺳﻼﻣﺖ ﺧﺎك ﻧﺎم ﺑﺮده ﻣﯽﺷﻮد. ﺑﻪﻫﻤﯿﻦ ﺟﻬﺖ، ﺑﺮرﺳﯽ ﺗﻮزﯾﻊ ﻣﮑﺎﻧﯽ ﮐﺮﺑﻦ آﻟﯽ ﺧﺎك، ﺟﻬﺖ ﺷﻨﺎﺳﺎﯾﯽ ﻣﻨﺎﻃﻖ ﺑﺎ ﭘﺘﺎﻧﺴﯿﻞ ﺗﺮﺳﯿﺐ ﮐﺮﺑﻦ، از اﻟﺰاﻣﺎت ﺑﺮﻧﺎﻣﻪرﯾﺰي ﻣﺪﯾﺮﯾﺖ ﺧﺎك و ﺳﯿﺎﺳﺖ ﮔﺬاري ﮐﻨﺘﺮل اﻗﻠﯿﻢ از ﻃﺮﯾﻖ ﻓﻌﺎﻟﯿﺖﻫﺎي ﮐﺸﺎورزي ﻣﯽﺑﺎﺷﺪ. روشﻫﺎي ﻣﺮﺳﻮم ﺑﺮآورد ﮐﺮﺑﻦ آﻟﯽ ﺧﺎك، ﭘﺮﻫﺰﯾﻨﻪ و زﻣﺎنﺑﺮ ﺑﻮده و ﻗﺎﺑﻠﯿﺖ ﺗﮑﺮار و ﺗﻌﻤﯿﻢ ﺑﻪ ﻧﻘﺎط ﻣﺸﺎﺑﻪ را ﻧﺪارد. در ﺳﺎلﻫﺎي اﺧﯿﺮ ﺑﺎ ﭘﯿﺸﺮﻓﺖ ﻓﻨﺎوري و ﻧﯿﺎز روز اﻓﺰون ﺑﺸﺮ ﺑﺮاي دﺳﺘﯿﺎﺑﯽ ﺑﻪ اﻃﻼﻋﺎت زودﯾﺎﻓﺖ و ﺻﺮﻓﻪﺟﻮﯾﯽ در ﻫﺰﯾﻨﻪ، از ﻃﺮﯾﻖ دادهﮐﺎوي و ﺑﻪ ﮐﻤﮏ ﺗﺼﺎوﯾﺮ ﻣﺎﻫﻮاره اي و ﻣﺘﻐﯿﺮﻫﺎي ﮐﻤﮑﯽ ﺗﻮﭘﻮﮔﺮاﻓﯽ، رﻗﻮﻣﯽﺳﺎزي وﯾﮋﮔﯽﻫﺎي ﺧﺎك از ﺟﻤﻠﻪ ﮐﺮﺑﻦ آﻟﯽ اﻣﮑﺎن ﭘﺬﯾﺮ ﺷﺪه اﺳﺖ. ﻧﻘﺸﻪ ﺑﺮداري رﻗﻮﻣﯽ ﺧﺎك در واﻗﻊ ﺗﻮﺳﻌﻪ ﯾﮏ ﻣﺪل ﻋﺪدي ﯾﺎ آﻣﺎري از راﺑﻄﻪ ﺑﯿﻦ ﻣﺘﻐﯿﺮﻫﺎي ﻣﺤﯿﻄﯽ و ﺧﺼﻮﺻﯿﺎت ﺧﺎك اﺳﺖ ﮐﻪ ﺑﺮاي داده ﻫﺎي ﺟﻐﺮاﻓﯿﺎﯾﯽ زﯾﺎدي ﺑﻪ ﻣﻨﻈﻮر ﺗﻮﻟﯿﺪ ﻧﻘﺸﻪ رﻗﻮﻣﯽ ﺑﻪ ﮐﺎر ﻣﯽرود. ﺳﻪ ﻫﺪف اﺻﻠﯽ ﻧﻘﺸﻪ ﺑﺮداري رﻗﻮﻣﯽ ﺧﺎك ﻋﺒﺎرت از: 1( اﺳﺘﻨﺒﺎط راﺑﻄﻪ ﺑﯿﻦ ﻣﺘﻐﯿﺮﻫﺎي ﻣﺤﯿﻄﯽ و ﺧﺼﻮﺻﯿﺎت ﺧﺎك، 2( ﺗﻮﻟﯿﺪ و اراﺋﻪ دادهﻫﺎﯾﯽ ﮐﻪ ﭘﯿﻮﺳﺘﮕﯽ ﺧﺎك- زﻣﯿﻦ ﻧﻤﺎ را ﺑﻬﺘﺮ ﻧﻤﺎﯾﺶ ﻣﯽدﻫﻨﺪ و 3( ﺑﻪ ﮐﺎرﮔﯿﺮي ﺻﺮﯾﺢ داﻧﺶ ﮐﺎرﺷﻨﺎس در ﻃﺮاﺣﯽ ﻣﺪل ﻣﯽﺑﺎﺷﻨﺪ. ﻫﻢ ﭼﻨﯿﻦ ﻧﻘﺸﻪ ﺑﺮداري رﻗﻮﻣﯽ ﺑﺎ اﯾﺠﺎد ﺑﯿﻨﺸﯽ در ﻣﻮرد ﻓﺮآﯾﻨﺪﻫﺎي ﺧﺎﮐﺴﺎزي، ﺑﺎﻋﺚ ﭘﯿﺸﺮﻓﺖ ﺑﺎﻟﻘﻮه ﭘﺪوﻟﻮژي و ﺟﻐﺮاﻓﯿﺎي ﺧﺎك ﻣﯽ ﺷﻮد. ﻣﻮاد و روش ﻫﺎ: اﯾﻦ ﻣﻄﺎﻟﻌﻪ در ﺷﻬﺮﺳﺘﺎن ﮐﺎﻣﯿﺎران اﺳﺘﺎن ﮐﺮدﺳﺘﺎن و ﺑﻪ ﻣﻨﻈﻮر ﭘﯿﺶ ﺑﯿﻨﯽ ﮐﺮﺑﻦ آﻟﯽ ﺧﺎك اﻧﺠﺎم ﺷﺪه اﺳﺖ. در اﯾﻦ ﭘﮋوﻫﺶ ﺗﻌﺪاد 110 ﻧﻤﻮﻧﻪ ﺧﺎك ﺑﺼﻮرت ﺗﺼﺎدﻓﯽ از ﮐﺎرﺑﺮيﻫﺎي ﻣﺨﺘﻠﻒ اراﺿﯽ ﻣﻮرد آﻧﺎﻟﯿﺰ ﻗﺮار ﮔﺮﻓﺖ. ﺑﺮاي ﭘﯿﺶﺑﯿﻨﯽ ﺑﻬﺘﺮ ﺗﻮزﯾﻊ ﻣﮑﺎﻧﯽ ﮐﺮﺑﻦ آﻟﯽ ﺧﺎك در ﻣﻨﻄﻘﻪ ﻣﻮردﻣﻄﺎﻟﻌﻪ از 101 ﻣﺘﻐﯿﺮ ﮐﻤﮑﯽ اﺳﺘﺨﺮاج ﺷﺪه از ﻣﺪل رﻗﻮﻣﯽ ارﺗﻔﺎع، ﺗﺼﺎوﯾﺮ ﻣﺎﻫﻮارهاي و ﻣﺘﻐﯿﺮﻫﺎي اﻗﻠﯿﻤﯽ ﻧﯿﺰ اﺳﺘﻔﺎده ﺷﺪه اﺳﺖ. ﭘﯿﺶﺑﯿﻨﯽ ﻣﻘﺪار ﮐﺮﺑﻦ آﻟﯽ ﺧﺎك ﺑﺎ دو ﻣﺪل رﮔﺮﺳﯿﻮن ﺧﻄﯽ ﭼﻨﺪ ﻣﺘﻐﯿﺮه و ﺷﺒﮑﻪ ﻋﺼﺒﯽ ﻣﺼﻨﻮﻋﯽ در ﻣﺤﯿﻂ ﻧﺮم اﻓﺰار ﺟﺎﻣﭗ ﻣﺪلﺳﺎزي ﺷﺪ. ﯾﺎﻓﺘﻪ ﻫﺎ: ﻧﺘﺎﯾﺞ ﻧﺸﺎن داد ﮐﻪ ﻣﻘﺪار ﮐﺮﺑﻦ آﻟﯽ ﺧﺎك در ﺑﺨﺶﻫﺎي ﻏﺮﺑﯽ و ﺷﻤﺎل ﻏﺮﺑﯽ ﻣﻨﻄﻘﻪ ﻣﻮردﻣﻄﺎﻟﻌﻪ، ﺑﯿﺶ ﺗﺮﯾﻦ ﻣﻘﺪار اﺳﺖ ﮐﻪ ﺷﺎﻣﻞ ﻣﻨﺎﻃﻖ ﺑﺎ ﭘﻮﺷﺶ ﺟﻨﮕﻠﯽ و ﻣﺮﺗﻌﯽ اﺳﺖ. ﻣﺘﻐﯿﺮﻫﺎي ﮐﻤﮑﯽ ﺳﻄﺢ ﭘﺎﯾﻪ ﺷﺒﮑﻪ ﮐﺎﻧﺎل )40%(، ﺑﺎﻧﺪ 4 ﺳﻨﺠﻨﺪه ،(% %23 )، مقدار آب برگ ( 20 %)، زبري زمين ( 19 %)، فاصله عمودي تا شبكه كانال ( 18 %)، شيب حوزه ( 18 )OLIﺷﺎﺧﺺ ﺗﻔﺎﺿﻞ ﻧﺮﻣﺎل ﺷﺪه ﭘﻮﺷﺶ ﮔﯿﺎﻫﯽ )17%(، ﺳﻄﺢ ﺣﻮزه )16%(، ﺟﻬﺖ ﺷﯿﺐ )16%(، ارﺗﻔﺎع )16%(، ﺑﺎﻧﺪ 3 )15%(، ﺷﺎﺧﺺ ﺟﺬب اﻧﻌﮑﺎﺳﯽ )14%(، ﺑﺎﻧﺪ 1 )14%(، ﺑﺎران )13%(، ﺑﺎﻧﺪ 5 )13%(، دﻣﺎي ﻫﻮا )12%(، ﺷﺎﺧﺺ ﭘﻮﺷﺶ ﮔﯿﺎﻫﯽ )11%(، ﺷﺎﺧﺺ ﺧﯿﺴﯽ ﺗﻮﭘﻮﮔﺮاﻓﯽ )10%( و ﺷﺎﺧﺺ ﺗﻔﺎﺿﻞ ﭘﻮﺷﺶ ﮔﯿﺎﻫﯽ )10%( ﺑﯿﺶ ﺗﺮﯾﻦ اﺛﺮ را روي ﻣﺪل ﺳﺎزي ﮐﺮﺑﻦ آﻟﯽ ﺧﺎك در ﻣﺪل ﺷﺒﮑﻪ ﻋﺼﺒﯽ ﻣﺼﻨﻮﻋﯽ داﺷﺘﻪاﻧﺪ. ﻧﺘﺎﯾﺞ اﻋﺘﺒﺎر ﺳﻨﺠﯽ ﻣﺪلﺳﺎزي ﻧﺸﺎن داد ﮐﻪ ﺷﺒﮑﻪ ﻋﺼﺒﯽ ﻣﺼﻨﻮﻋﯽ ﻋﻤﻠﮑﺮد ﺑﻬﺘﺮي )0/97 =R2( ﻧﺴﺒﺖ ﺑﻪ رﮔﺮﺳﯿﻮن ﺧﻄﯽ ﭼﻨﺪ ﻣﺘﻐﯿﺮه )0/59 =R2( ﺑﺮاي ﭘﯿﺶﺑﯿﻨﯽ ﮐﺮﺑﻦ آﻟﯽ ﺧﺎك در ﻣﻨﻄﻘﻪ ﻣﻮرد ﻣﻄﺎﻟﻌﻪ داﺷﺘﻪ اﺳﺖ.
ﻧﺘﯿﺠﻪ ﮔﯿﺮي: ﻧﺘﺎﯾﺞ اﯾﻦ ﭘﮋوﻫﺶ ﻧﺸﺎن داد ﮐﻪ ﭘﺮاﮐﻨﺶ ﮐﺮﺑﻦ آﻟﯽ ﺑﯿﺶ ﺗﺮ ﺗﺤﺖ ﺗﺄﺛﯿﺮ ﻋﻮاﻣﻞ ﺗﻮﭘﻮﮔﺮاﻓﯽ و اﻗﻠﯿﻢ ﻣﯽﺑﺎﺷﺪ. در ﻣﻨﺎﻃﻘﯽ ﮐﻪ ﺑﻪ ﻫﺮ دﻟﯿﻞ اﻣﮑﺎن ﻧﻤﻮﻧﻪﺑﺮداري در ﮐﻞ ﻣﻨﻄﻘﻪ وﺟﻮد ﻧﺪارد، ﻣﯽﺗﻮان از ﻃﺮﯾﻖ ﻣﺘﻐﯿﺮﻫﺎي ﮐﻤﮑﯽ ﻣﺎﻧﻨﺪ ﭘﺎراﻣﺘﺮﻫﺎي ﺗﻮﭘﻮﮔﺮاﻓﯽ، اﻗﻠﯿﻤﯽ و ﭘﻮﺷﺶ ﮔﯿﺎﻫﯽ و ﺑﺎ روشﻫﺎي ﻧﻮﯾﻦ دادهﮐﺎوي ﺑﺮاي ﺗﺨﻤﯿﻦ ﮐﺮﺑﻦ آﻟﯽ ﺧﺎك ﺑﻬﺮه ﮔﺮﻓﺖ.
چكيده لاتين :
Background and Objectives: Soil organic carbon plays a vital role in climate control and environmental sustainability. It also has a key impact on the physico-chemical and biological properties of the soil as it is considered an indicator of soil health. Therefore, investigating the spatial distribution of soil organic carbon is one of the requirements of climate and soil management planning. Traditional methods of estimating soil organic carbon are costly and time consuming and cannot be replicated and extended to similar locations. With the advancement of technology and the ever-increasing need for cost-effective information, data mining and satellite imagery and land parameters have been digitized by soil features. Digital soil mapping is the development of a numerical or statistical model of the relationship between environmental variables and soil properties that is used for large geographic data to generate a digital map. The three main goals of soil digital mapping are: 1) inferring the relationship between environmental variables and soil characteristics, 2) producing and presenting data that better demonstrate soil-geography coherence, and 3) applying expert knowledge in model design. Digital mapping also develops the potential of pedology and soil geography by creating insights into burial processes.
Materials and Methods: In this study 110 soil samples along with 101 auxiliary parameters were used to predict soil organic carbon in Kamyaran city (Kurdistan province). Multivariate linear regression models and artificial neural networks were modeled using JMP software.
Results: The results showed that soil organic carbon content was highest in the western and northwestern parts of the study area and was related to forest cover and pasture areas. On the other hand, higher altitudes have higher estimated organic carbon. Auxiliary variables of the channel network base level (40%), band 4 (23%), leaf water content (20%), vector terrain roughness (19%), vertical distance to channel network (18%), catchment slope (18%), Normalized vegetation difference index (17%), catchment area (16%), aspect (16%), dem (16%), band 3 (15%), reflectance absorption index (14%), band 1 (14) %), Rain (13%), band 5 (13%), air temperature (12%), vegetation index (11%), topographic wetness index (10%), vegetation index (10%) and so on had the greatest effect on soil organic carbon modeling, in the artificial neural network model. Modeling soil organic carbon distribution by artificial neural network (R2 = 0.97) performed better than multivariate linear regression (R2 = 0.59). Conclusion: The results of this study showed that the distribution of organic carbon is more influenced by topographic, vegetation and climate factors. In areas where sampling is not possible in the whole area for any reason, it can be used through environmental data such as topographic, climatic and vegetation parameters and with new data mining methods to estimate soil organic carbon.
