Evaluation Of Soil Fertility In Suzhou Area Via Artificial Neural Network

Suzhou is located in the Yangtze River Delta,Shanghai to the east,Zhejiang to the south,Taihu Lake to the west,Yangtze River to the north and Taihu Lake Basin,which belongs to the north subtropical monsoon humid climate zone with mild and humid climate.The total area of the city is 8488.42 km2,of which 55%are plains,42%are water surface,3%are hills,and the average elevation is 4 meters.Geomorphological characteristics of the plain as the top,the city’s low and flat terrain,fertile land,rich in products.Agricultural utilization area is the largest in the land use situation of the whole city.According to the 2nd national soil(general)survey,soils in Suzhou include 5 soil group,8 subgroup and 31 soil genus.There are about 1633 km2 of cultivated land in Suzhou,mainly planting rice,cotton,rape,wheat and vegetables.In recent years,with the rapid development of industrial economy and urbanization,the area of agricultural production has been gradually reduced,and the planting system has remained stable.The main system is continuous cropping of rice and wheat,cotton and wheat,rice oil and vegetables.In this study,soil samples were collected from 65 conventional fertilization areas of 65 provincial and municipal monitoring points of cultivated land quality in Suzhou,Jiangsu Province.65 soil samples were obtained.Organic matter,total nitrogen,total phosphorus,total potassium,alkali-hydrolyzed nitrogen,available phosphorus,available potassium and pH value were determined.Artificial neural network was used to study the soil samples.The soil fertility quality was calculated and analyzed to realize the automation of soil fertility evaluation.The results show that although the soil fertility quality in different regions of Suzhou has some differences,the overall soil fertility in Suzhou is relatively good,preferring to type I land.Soil physical and chemical properties such as organic matter,total nitrogen,total phosphorus,total potassium,alkali-hydrolyzed nitrogen,available phosphorus,available potassium and pH value have a certain degree of spatial variability in the region of Suzhou.Through the analysis of soil pH,organic matter and other nutrient data in 2007,2011,2014,2016 and 2017,it is found that the soil pH shows a downward trend.In 2017,the soil pH decreases to 6.68.The soil organic matter,total nitrogen,alkali hydrolyzed nitrogen,available phosphorus and available potassium all increased,compared with last contrary,about 13%,60%,66%,32%and 51%respectively.Through BP artificial neural network and the calculation of the membership degree of soil fertility quality,it is found that the membership degree of the overall soil fertility quality in Suzhou is at or above level III,Changshu,Taicang,Wujiang and Wuzhong are among level I and level III,all of which are biased to level I,Kunshan and Zhangjiagang are biased to level III,and the overall soil fertility quality in Suzhou is biased to level I.The results of this study can provide guidance for soil improvement and formula fertilization in Suzhou,.It can provide an important theoretical basis for improving soil fertility,and then determine the most reasonable land use model,improve the utilization rate of land resources,which is of great significance for the green development of agriculture and sustainable agriculture.