scholarly journals Machine learning for predicting soil classes in three semi-arid landscapes

Geoderma ◽  
2015 ◽  
Vol 239-240 ◽  
pp. 68-83 ◽  
Author(s):  
Colby W. Brungard ◽  
Janis L. Boettinger ◽  
Michael C. Duniway ◽  
Skye A. Wills ◽  
Thomas C. Edwards
Keyword(s):  
Machine Learning ◽  
Arid Landscapes ◽  
Semi Arid

Patterns of territory settlement by Eurasian scops-owls (Otus scops) in altered semi-arid landscapes

2007 ◽  
Vol 69 (3) ◽  
pp. 400-409 ◽  
Author(s):  
J.A. Martínez ◽  
I. Zuberogoitia ◽  
J.E. Martínez ◽  
J. Zabala ◽  
J.F. Calvo
Keyword(s):  
Arid Landscapes ◽  
Semi Arid

Pollen diversity and protein content in differentially degraded semi-arid landscapes in Kenya

2021 ◽  
pp. 1-14
Author(s):  
Pamela Ochungo ◽  
Ruan Veldtman ◽  
Rahab Kinyanjui ◽  
Elfatih M. Abdel-Rahman ◽  
Eliud Muli ◽  
...  
Keyword(s):  
Protein Content ◽  
Arid Landscapes ◽  
Semi Arid

Concentration and Nitrogen Stocks in the Soils of Semi-Arid Landscapes of Kizlyar Pastures

2020 ◽  
pp. 66-74
Author(s):  
Tatiana A. Asvarova ◽  
Gasan N. Gasanov ◽  
Kabirat B. Gimbatova ◽  
Kamil M. Hajiev ◽  
Rashid R. Bashirov ◽  
...  
Keyword(s):  
Total Nitrogen ◽  
Humus Horizon ◽  
Control Area ◽  
Climatic Conditions ◽  
Chestnut Soils ◽  
Number Of Species ◽  
Current State ◽  
Low Degree ◽  
Arid Landscapes ◽  
Semi Arid

The results of research on the current state of the nitrogen fund (reserve regime) the Kizlyar pastures. It was found that the total nitrogen ranges from 0.15-0.2 %, nitrogen easily hydrolyzed from 2.4-5.3 mg/100g in light-chestnut, meadow-chestnut soils and saline typical, and has a medium and low degree of security. The humus horizon is more enriched with nitrogen on soils of meadow-chestnut and light-chestnut compared to typical saline. N and C reserves in the soil in spring are 5.0 and 13.4 t/ha, respectively, and in autumn N and C reserves are 1.5 times lower, due to decrease the number of species and projected coverage up to 40-50% of phytocenoses in autumn, and also depends on the climatic conditions of the annual seasonality. In the control area with intensive grazing, nitrogen and carbon reserves in the soil are 1.6-1.8 times lower.

scholarly journals Machine Learning to Estimate Surface Soil Moisture from Remote Sensing Data

Water ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 3223
Author(s):  
Hamed Adab ◽  
Renato Morbidelli ◽  
Carla Saltalippi ◽  
Mahmoud Moradian ◽  
Gholam Abbas Fallah Ghalhari
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Soil Moisture ◽  
Surface Soil ◽  
Remote Sensing Data ◽  
Surface Soil Moisture ◽  
Machine Learning Methods ◽  
Land Use Types ◽  
Semi Arid Region ◽  
Semi Arid

Soil moisture is an integral quantity parameter in hydrology and agriculture practices. Satellite remote sensing has been widely applied to estimate surface soil moisture. However, it is still a challenge to retrieve surface soil moisture content (SMC) data in the heterogeneous catchment at high spatial resolution. Therefore, it is necessary to improve the retrieval of SMC from remote sensing data, which is important in the planning and efficient use of land resources. Many methods based on satellite-derived vegetation indices have already been developed to estimate SMC in various climatic and geographic conditions. Soil moisture retrievals were performed using statistical and machine learning methods as well as physical modeling techniques. In this study, an important experiment of soil moisture retrieval for investigating the capability of the machine learning methods was conducted in the early spring season in a semi-arid region of Iran. We applied random forest (RF), support vector machine (SVM), artificial neural network (ANN), and elastic net regression (EN) algorithms to soil moisture retrieval by optical and thermal sensors of Landsat 8 and knowledge of land-use types on previously untested conditions in a semi-arid region of Iran. The statistical comparisons show that RF method provided the highest Nash–Sutcliffe efficiency value (0.73) for soil moisture retrieval covered by the different land-use types. Combinations of surface reflectance and auxiliary geospatial data can provide more valuable information for SMC estimation, which shows promise for precision agriculture applications.

A flow-filter model for simulating the conservation of limited resources in spatially heterogeneous, semi-arid landscapes

1994 ◽  
Vol 1 (3) ◽  
pp. 209 ◽  
Author(s):  
John A. Ludwig ◽  
David J. Tongway ◽  
Stephen G. Marsden
Keyword(s):  
Water Conservation ◽  
Plant Production ◽  
Landscape Model ◽  
Filter Model ◽  
Landscape Degradation ◽  
Available Water ◽  
High Resource ◽  
Arid Landscapes ◽  
Minimal Area ◽  
Semi Arid

As in arid lands of the world, many semi-arid landscapes in Australia have plant and animal growth and reproduction, hence survival, severely limited by available water. For example, Acacia anuera (mulga) grove-intergrove landscapes are source-sink systems where water flows from low ridges and stony slopes (inter-groves) into flat areas (groves). Water can be lost from these systems, to lakes and rivers. This occurs if the water retention (filtering and storage) capacity of the sinks is too low (perhaps due to landscape degradation) or if the total area of sink is too small. A flow-filter landscape model was developed to determine the area of sink (relative to the total area) that will maximize resource (water) conservation and plant production under conditions of low rainfall. The model was also used to examine the effect of having landscape resource sinks with low and high filtering capacities. Simulation results indicate that when rainfall is low (160 mm) the area of sink needed to conserve all available water within the landscape was 40 per cent of the total landscape area when sinks had high resource-filtering capacities; this area increased to 60 per cent when sinks had a low filtering capacity as the case with landscape degradation. The flow-filter landscape model can provide land managers with guidelines on rehabilitating degraded landscapes by reconstruction of sink areas. To conserve the limited amounts of rainfall within a semi-arid landscape a minimal area of sink has to be reconstructed; the flow-filter model estimates this minimal area, thus reducing rehabilitation costs.

Flow and Sediment Connectivity in Semi-arid Landscapes in SE Spain: Patterns and Controls

2015 ◽  
Vol 27 (4) ◽  
pp. 1032-1044 ◽  
Author(s):  
Miguel Marchamalo ◽  
Janet M. Hooke ◽  
Peter J. Sandercock
Keyword(s):  
Se Spain ◽  
Sediment Connectivity ◽  
Arid Landscapes ◽  
Semi Arid
Sign in / Sign up

Export Citation Format

Share Document