Water is a fundamental natural resource while agriculture water guarantees the grain output, which shows that the utilization and management of water resource have a significant practical meaning. Regional agricultural water resource system features with unpredictable, self-organization, and non-linear which lays a certain difficulty on the evaluation of regional agriculture water resource resilience. The current research on water resource resilience remains to focus on qualitative analysis and the quantitative analysis is still in the primary stage, thus, according to the above issues, projection pursuit classification model is brought forward. With the help of artificial fish-swarm algorithm (AFSA), it optimizes the projection index function, seeks for the optimal projection direction, and improves AFSA with the application of self-adaptive artificial fish step and crowding factor. Taking Hongxinglong Administration of Heilongjiang as the research base and on the basis of improving AFSA, it established the evaluation of projection pursuit classification model to agriculture water resource system resilience besides the proceeding analysis of projection pursuit classification model on accelerating genetic algorithm. The research shows that the water resource resilience of Hongxinglong is the best than Raohe Farm, and the last 597 Farm. And the further analysis shows that the key driving factors influencing agricultural water resource resilience are precipitation and agriculture water consumption. The research result reveals the restoring situation of the local water resource system, providing foundation for agriculture water resource management.

A Projection Pursuit Classification model optimized by the Cat Swarm Optimization algorithm (CSO-PPC) was proposed to evaluate system resilience in Hongxinglong Administration of Heilongjiang Province, China. Meanwhile, the driving forces behind resilience were analyzed using Principal Component Analysis (PCA). CSO-PPC was used to evaluate resilience for the 12 farms in Hongxinglong Administration, and PCA was applied to select the key factors driving their resilience. Results showed that the key factors were per capita water, unit area grain yield, application of fertilizer per unit cultivated area and the proportion of cultivated land, which were closely related to human production and planting area. Overall water resources system resilience improved by 2011 compared to 2005. Specifically, water resources system resilience grades for the 12 farms were divided into five levels from inferior to superior, i.e. I to V. After six years of development, the resilience of eight farms had improved. Farm Youyi and Farm 853 were upgraded from inferior level II to the best level V. However, according to the data, four farms still had low resilience that had not improved in recent years. Further results showed that the driving forces decreased from 1998 to 2003 and increased from 2003 to 2011.

Water resources are an important influence factor of land remediation. As support of food production, analysis of water resources supply and demand balance is an important part and technical support of the construction. According to some relevant calculation formulas on water resources assessment, after forecast of water demand and the calculation of water supply, in the project area of the demonstration construction of whole rural land remediation in Baishan City, the average water availability for many years is 8990.1 thousand m3 each year, in which surface water availability is 7210.6 thousand m3, groundwater availability is 1579.4 thousand m3. Water demand is 5552.4 thousand m3 in 2015, in which water demand for life 4165.2 thousand m3; water demand for agricultural irrigation is 1387.2 thousand m3. Water supply is more than water demand; the results show that there is a slight surplus of water resources in the region. The basic supply-demand balance can be achieved in conditions of the design of water supply project in the project area.

Water resources are an important influence factor of land remediation. As support of food production, analysis of soil and water resources supply and demand balance is an important part and technical support of the construction. According to some relevant calculation formulas on water resources assessment, after forecast of water demand and the calculation of water supply, in the project area of the demonstration construction of whole rural land remediation in Fuyu County, the average water availability for many years is 70581.6 thousand m3 each year, including surface water availability 57003.3 thousand m3 and groundwater availability 13578.3 thousand m3. Water demand is 58806.2 thousand m3 in 2015; including water demand for life 5150.9 thousand m3 and water demand for agricultural irrigation 53655.3 thousand m3. Water supply is more than water demand; the basic supply-demand balance can be achieved in conditions of the design of water supply project.