Modeling Apparent Nitrogen Mineralization under Field Conditions Using Regressions and Artificial Neural Networks

Abstract

Soil N mineralization is an important source of N for grain crops, but its estimation under fi eld conditions is usually very difficult. Our objective was to develop models suitable for predicting N mineralization during the growing seasons of wheat (Triticum aestivum L.) and corn (Zea mays L.) under fi eld conditions. Fift y-eight fi eld experiments were performed with wheat, and 35 with corn, along three growing seasons, in which soil apparent N mineralization was estimated by the mass balance approach. Apparent nitrogen mineralized from decomposing residues (ANMR) or soil humic substances (ANMH) were estimated separately. Two empirical modeling techniques were tested, linear regression and artifi cial neural networks, using as independent variables or inputs some environmental variables. Both techniques allowed the development of suitable models for N mineralization prediction (R 2 > 0.68), but neural networks gave slightly better results. Th e ANMR ranged from −42 to 64 kg N ha −1 , increasing as residue mass and N concentration increased. An average ANMR of 15 to 16 kg N ha −1 was produced both during wheat and corn growing seasons. Th e ANMH ranged from −80 to 328 kg N ha −1 , being on average four times greater during corn growing cycle than during wheat season (127 vs. 34 kg N ha −1 ). Th e ANMH decreased as initial mineral N content of the soil, remaining residue mass or fi ne particles content of the soil increased, and it was greater in soils of higher organic matter level and mineralization potential, as determined by an incubation test. Increases in temperature and rainfall also determine greater ANMH. Th e methodology developed for apparent N mineralization estimation may be applied to other crops and production regions.

Assessment of apparent N mineralization at field scale

“…There was no relationship between soil initial-N and DANM, which contrasts with other researches conducted in the humid regions of the Pampas, in which initial-N controlled the apparent N mineralization (Alvarez & Steinbach, 2011;Gonzalez Montaner et al, 1997). It is possible the latter results were caused by a larger initial soil N content than that observed in the current study.…”

Development of a Regional Soil Productivity Index Using an Artificial Neural Network Approach

“…Organic matter has a positive influence on wheat yield; this might be a possible consequence of its function as a nutrient source. In the Pampas, it was demonstrated that at the time of wheat sowing, NO 3 levels were higher in C‐rich soils (Alvarez et al, 2002) and as organic matter increased, the capacity of the soils to mineralize N during wheat growing cycle increased (Alvarez and Steinbach, 2011). As we observed at the regional scale for the Pampas, significant relationships of soil organic C and crop yield were established in other studies from other parts of the world (García‐Paredes et al, 2000); however, this relation was not established in all regions (Jiang and Thelen, 2004), and this could be associated with soil C gradients and management conditions (low or high fertilizer consumption).…”

Potential of mineralization of Nitrogen from soils of Huanuco, Peru

“…Dendograma de similaridad de los sitios según los porcentajes de mineralización de N evaluadas mediante distancia de Ward. Álvarez & Steinbach (2011) también indicaron que la actividad microbiana de los suelos es más lenta en condiciones de climas fríos y con baja humedad, reduciendo con ello el proceso de mineralización de la materia orgánica. Las altas temperaturas y bajos contenidos de arcillas en el suelo también aceleran la mineralización de la materia orgánica (Reussi Calvo et al, 2018).…”