Reducing environmental risk by improving N management in intensive Chinese agricultural systems

Abstract

Excessive N fertilization in intensive agricultural areas of China has resulted in serious environmental problems because of atmospheric, soil, and water enrichment with reactive N of agricultural origin. This study examines grain yields and N loss pathways using a synthetic approach in 2 of the most intensive double-cropping systems in China: waterlogged rice/upland wheat in the Taihu region of east China versus irrigated wheat/rainfed maize on the North China Plain. When compared with knowledge-based optimum N fertilization with 30-60% N savings, we found that current agricultural N practices with 550-600 kg of N per hectare fertilizer annually do not significantly increase crop yields but do lead to about 2 times larger N losses to the environment. The higher N loss rates and lower N retention rates indicate little utilization of residual N by the succeeding crop in rice/wheat systems in comparison with wheat/maize systems. Periodic waterlogging of upland systems caused large N losses by denitrification in the Taihu region. Calcareous soils and concentrated summer rainfall resulted in ammonia volatilization (19% for wheat and 24% for maize) and nitrate leaching being the main N loss pathways in wheat/maize systems. More than 2-fold increases in atmospheric deposition and irrigation water N reflect heavy air and water pollution and these have become important N sources to agricultural ecosystems. A better N balance can be achieved without sacrificing crop yields but significantly reducing environmental risk by adopting optimum N fertilization techniques, controlling the primary N loss pathways, and improving the performance of the agricultural Extension Service.

Fig. 1.

Relationships of N recovery rate (A), loss rate (B), and retention rate (C) with N application rate in 4 crops (Field Study 2). Vertical bars denote standard deviation of the mean (average of 6 ¹⁵N field experiments). Each model fitting produced a highly significant model (P < 0.01).