The assessment of spatial distribution of soil salinity risk using neural network

Abstract

Soil salinity in the Aral Sea Basin is one of the major limiting factors of sustainable crop production. Leaching of the salts before planting season is usually a prerequisite for crop establishment and predetermined water amounts are applied uniformly to fields often without discerning salinity levels. The use of predetermined water amounts for leaching perhaps partly emanate from the inability of conventional soil salinity surveys (based on collection of soil samples, laboratory analyses) to generate timely and high-resolution salinity maps. This paper has an objective to estimate the spatial distribution of soil salinity based on readily or cheaply obtainable environmental parameters (terrain indices, remote sensing data, distance to drains, and long-term groundwater observation data) using a neural network model. The farm-scale (∼15 km(2)) results were used to upscale soil salinity to a district area (∼300 km(2)). The use of environmental attributes and soil salinity relationships to upscale the spatial distribution of soil salinity from farm to district scale resulted in the estimation of essentially similar average soil salinity values (estimated 0.94 vs. 1.04 dS m(-1)). Visual comparison of the maps suggests that the estimated map had soil salinity that was uniform in distribution. The upscaling proved to be satisfactory; depending on critical salinity threshold values, around 70-90% of locations were correctly estimated.

Mapping abandoned agricultural land in Kyzyl-Orda, Kazakhstan using satellite remote sensing

“…In comparison with other ex-Soviet Union countries Baumann et al, 2011;Kuemmerle et al, 2008; and other regions worldwide (Falcucci, Maiorano, & Boitani, 2006;Park & Egbert, 2008), only few studies map abandoned cropland in CA (Akramkhanov & Vlek, 2012;De Beurs, Henebry, & Debeurs, 2004). In Kazakhstan, which is the largest producer of wheat and rice in the region and the third largest producer of cotton lint in CA (FAO, 2015), the causes of cropland abandonment and the spatial patterns of abandoned cropland are largely ill-understood (Anderson & Swinnen, 2008).…”

SPOT-Based Sub-Field Level Monitoring of Vegetation Cover Dynamics: A Case of Irrigated Croplands

“…Causes of the vegetation cover decline observed in the remaining 15,247 ha of cropping area in the region must be verified through further in situ field investigation. Attention should be directed at both LD processes such as soil salinization as well as changes in agricultural management practices [70].…”

Agricultural Soil Alkalinity and Salinity Modeling in the Cropping Season in a Spectral Endmember Space of TM in Temperate Drylands, Minqin, China

“…The results indicate that the various spectral reflectance combinations (indices) and methods performed inconsistently [11]. Some multispectral studies have also combined soil environmental covariates in agricultural soil salinity assessment models (e.g., [10,17]). However, the contribution of individual covariates can be inconsistent [18], partly due to the mismatch of spatio-temporal resolution and the quality of ancillary data [10].…”

“…Soil salinity and soil reflectance can be approximated by a linear function in the absence of the disturbance of other environmental variables, and thus, there is a large similarity between the two approaches, and PLSR has the advantage of relative simplicity compared to ANN [26]. The advantage of ANN is its nonlinear quantification of complex processes at the regional scale, and it was successfully used to estimate the spatial distribution of soil salinity based on complex environmental parameters (terrain indices, distance to drains, and long-term groundwater observation data) with ETM+ data (vegetation index, the raw bands 3 and 5) [17]. In addition, the stable and easy-to-interpret SVD can possibly reduce the shortcomings of ANN as a "black box" approach [27], and its requirement of large training samples [28].…”