Soil Data Research Articles

An Improved Reptile Search Algorithm with Multiscale Adaptive Deep Learning Technique and Atrous Spatial Pyramid Pooling for IoT-based Smart Agriculture Management

Smart farming is an enhanced option for increasing food production, resource management and labour. Existing prediction methods need trained experts to analyse the data, which is a time-consuming process, and thus, there is a need for smart farming with the Internet of Things (IoT). Hence, a well-developed IoT-assisted smart agriculture model is proposed for managing agricultural needs to improve the economic value of farmers. The proposed framework constitutes four major aspects like Crop prediction, Crop yield prediction, Plant disease prediction and Smart irrigation. Initially, the crop images are taken as the input and fed to the Multi-scale Adaptive and Attention-based Convolution Neural Network with Atrous Spatial Pyramid Pooling (MACNN-ASPP), where the dissimilar crops are classified and obtained. In the second aspect, the crop image as well as crop-related data, are fetched from the data sources and given as input. Further, the deep features of the image are extracted that are added with soil and environment condition data. Then this feature is subjected to the Multi-scale Adaptive and Attention-based One-Dimensional Convolution Neural Network with Atrous Spatial Pyramid Pooling (MA1DCNN-ASPP) for crop yield prediction. While in the third aspect, the leaf images are assembled from the data file and fed as input to the MACNN-ASPP for detecting the variety of diseases affecting the plants. In the final aspect, smart irrigation is done by collecting field images with related data. Further, the deep features retrieved from the field images are applied to MA1DCNN-ASPP, where the different conditions of the field will be attained. In order to develop the model adaptively, the hyper-parameters in the network are optimised using the Improved Reptile Search Algorithm (IRSA). Finally, the investigation is done over the proposed methodology using multiple evaluation metrics. In contrast with other approaches, the proposed smart agriculture outperforms the performance of managing crops without any hazardous effects. Accuracy validation executed in the implemented IRSA-MACNN-ASSP-based crop yield prediction model accomplished better efficiency as 6.89%, 4.45%, 2.19% and 1.08% better than the classical techniques like CNN, LSTM, 1DCNN and MA1DCNN-ASPP.

Identification of Spatial Patterns of Soil Erosion Based on the Combination of RUSLE and MCDA in the Ahferom District, Northern Ethiopia

Soil erosion is a widespread concern that is indeed considered to be a significant environmental issue, and it has particularly severe consequences in less developed countries like Ethiopia. An effective watershed management procedure for establishing priority is supported by the identification of erosion-susceptible areas. Therefore, the main objective of the study was to assess soil erosion dynamics and its spatial pattern using a novel methodological framework combining the RUSLE and MCDA. The study used data on land use and cover, topography, soil, and climatic data. The analytical hierarchy process (AHP) were used to identify soil erosion-susceptible areas and the factors were weighted using a pairwise comparison matrix, and weights were combined using weighted overlay in GIS. Our results indicated that the mean annual soil loss rate was 27.10 t ha−1 yr−1, while the total soil loss from the entire study area was 3.11 Mt. The highest soil loss was observed in bare land (30.54 t ha−1 yr−1) and farmland (23.65 t ha−1 yr−1), which were considered as the most susceptible land types to erosion. Likewise, 10.3% of the study area is very highly susceptible; 20.2% is highly susceptible, 24.2% of the area is moderately susceptible, 27.1% is low, and 18.2% has very low susceptibility. The district’s most significant erosion-susceptible areas are characterized by steep slopes that are composed of farmland and bare land. This suggests the majority of the area is susceptible to erosion, requiring interventions to reverse the alarming degradation level. The presented framework has a board application to estimate regional soil erosion and to identify spatial patterns of soil erosion.

Quantitative Analysis about the Spatial Heterogeneity of Water Conservation Services Function Using a Space–Time Cube Constructed Based on Ecosystem and Soil Types

Precisely delineating the spatiotemporal heterogeneity of water conservation services function (WCF) holds paramount importance for watershed management. However, the existing assessment techniques exhibit common limitations, such as utilizing only multi-year average values for spatial changes and relying solely on the spatial average values for temporal changes. Moreover, traditional research does not encompass all WCF values at each time step and spatial grid, hindering quantitative analysis of spatial heterogeneity in WCF. This study addresses these limitations by utilizing an improved water balance model based on ecosystem type and soil type (ESM-WBM) and employing the EFAST and Sobol’ method for parameter sensitivity analysis. Furthermore, a space–time cube of WCF, constructed using remote-sensing data, is further explored by Emerging Hot Spot Analysis for the expression of WCF spatial heterogeneity. Additionally, this study investigates the impact of two core parameters: neighborhood distance and spatial relationship conceptualization type. The results reveal that (1) the ESM-WBM model demonstrates high sensitivity toward ecosystem types and soil data, facilitating the accurate assessment of the impacts of ecosystem and soil pattern alterations on WCF; (2) the EHSA categorizes WCF into 17 patterns, which in turn allows for adjustments to ecological compensation policies in related areas based on each pattern; and (3) neighborhood distance and the type of spatial relationships conceptualization significantly impacts the results of EHSA. In conclusion, this study offers references for analyzing the spatial heterogeneity of WCF, providing a theoretical foundation for regional water resource management and ecological restoration policies with tailored strategies.

Temporal and Spatial Variations of Soil Organic Carbon and the Influencing Factors in Shaanxi Province in Recent 30 Years

Soil organic carbon （SOC） variation is a significant indicator for the soil quality dynamic and global carbon cycle. Therefore, it is necessary to study the regional temporal and spatial distribution of SOC pool and the influencing factors. In this study, a total of 540 soil data and environmental variables were collected from Shaanxi Province during a 30-year period from 1985 to 2015, and univariate analysis of variance and path analysis were used to explore the temporal and spatial distribution characteristics of SOC content and the influencing factors of SOC change. The results showed that the SOC contents of Shaanxi Province in both 1985 and 2015 were the highest in central Shaanxi, followed by those in southern Shaanxi, and they were significantly higher than those in northern Shaanxi. From 1985 to 2015, the increase in SOC in southern Shaanxi was the highest （21.28%）, and that in central Shaanxi was 15.33%. The content of SOC in northern Shaanxi was decreased by 10.23%, caused by significant decrements in the bottom horizons of 60-80 cm and 80-100 cm. Compared with that in 1985, the increases in SOC content in the 0-100 cm soil profile （with every 20 cm as a horizon） ranged from 3.21% to 29.39% in 2015. The increase in SOC content of skeletal soils was largest, followed by that of alluvial soils. Correlation analysis and path analysis showed that SOC content was positively correlated with altitude, average annual precipitation, normalized vegetation index, and total nitrogen content and was in significant negative correlation with curvature, bulk density, and pH. Total nitrogen content was the main controlling factor affecting SOC content. The results of the study can provide reference for future carbon management measures in the region.

Soil erodibility mapping using remote sensing and in situ soil data with random forest model in a mountainous catchment of Indian Himalayas.

Land degradation is accelerating in the Himalayan ecosystem, resulting in the loss of soil nutrients due to severe erosion. Soil erosion presents a significant environmental challenge, resulting in both on-site and off-site consequences, such as reduced soil productivity and siltation in reservoirs. Soil erodibility (K factor), an inherent soil property, determines the susceptibility of soils to erosion. Sampling across hilly and mountainous terrain pose challenges due to its complex landscape. Despite these challenges, it is essential to study K factor variations in different land use/land cover types to comprehend the threat of erosion. Digital soil mapping offers an opportunity to overcome this limitation by providing spatial predictions of soil properties. The objective of our study is to map the spatial distribution of soil erodibility using the Random Forest (RF) model, a machine learning method based on sampled in situ soil data and environmental covariates. We collected 556 surface soil samples from the mountainous catchment (Tehri dam catchment) using the stratified random sampling approach. The model performed satisfactorily in both training (r2 = 0.91; RMSE = 0.00185) and testing (r2 = 0.45; RMSE = 0.00318) phases. Subsequently, we generated a digital map with a resolution of 12.5m to depict the distribution of the K factor. Our analysis revealed that key environmental variables influencing the prediction of the K factor included geology, mean NDVI, and climatic factors. The average K factor value was estimated at 0.0304 and ranging from 0.0251 to 0.0400 t ha h ha-1MJ-1mm-1. A higher K factor was observed in the barren land (0.0344) primarily located in the higher and trans-Himalayan region of seasonally snow-covered areas. These areas typically feature young soils with weak soil formation and unstable soil aggregates. Subsequently cropland/cultivated soils (0.0307) exhibited higher K factor values due to the breakdown of soil aggregates by ploughing activities and exposing carbon to decomposition. The average K factor value of evergreen (0.0294) and deciduous (0.0295) forests were the lowest compared to other land use/land cover types indicating the role of forests in resisting soil erosion. By assessing and predicting soil erodibility, land planners and farmers can implement erosion control measures to protect soil health, prevent sedimentation in water bodies, and sustain agricultural productivity in the Himalayas.

Runoff Estimation in Kajurli Watershed Using SCS-CN and GIS Techniques

The study focuses on estimating surface runoff using the Soil Conservation Service Curve Number (SCS-CN) method, combined with Remote Sensing (RS) and Geographic Information System (GIS) techniques, for the Kajurli Watershed in Ratnagiri District, Maharashtra. Surface runoff is a key factor influencing agricultural productivity, soil erosion, and water management at the watershed level. The SCS-CN method, a widely used tool for runoff estimation, utilizes rainfall, land use, and soil type data. By integrating RS and GIS, the study achieves a more accurate assessment of land use and soil characteristics, which are critical inputs for runoff calculations. The Kajurli Watershed falls under hydrological soil group B, known for moderate runoff potential. The study uses 33 years of historical rainfall data (1990-2022) to compute annual runoff using the SCS-CN method. Key parameters such as Curve Numbers (CN) are derived based on land use, hydrological soil groups, and antecedent moisture conditions (AMC). The average annual rainfall in the watershed is found to be 3392.8 mm, with 39.69% of this rainfall contributing to surface runoff. The integration of RS and GIS simplifies spatial analysis, enabling accurate and efficient runoff estimation. The study highlights the sensitivity of the SCS-CN method to CN values, emphasizing the importance of precise land use and soil data for reliable hydrological modelling. These findings offer crucial insights for water resource management, flood control, and agricultural planning in the region.

APD: An automated parameter determination system based on in-situ tests

In-situ testing has numerous applications in geotechnical engineering. The interpretation of in-situ test results includes soil stratification and determination of soil parameters. This paper presents an automated parameter determination framework that aims to determine constitutive model parameters based on in-situ tests. The ongoing research project relies on a graph-based approach for determining the parameters. The framework has two main attributes: transparency and adaptability. Transparency is achieved by illustrating how a certain parameter was computed. Adaptability is ensured by allowing users to incorporate their expertise into the framework. The system currently determines parameters based on three main workflows that utilize the results of cone penetration tests, dilatometer tests, and shear wave velocity measurements. This study employs the three main workflows to determine soil parameters for one of the Norwegian GeoTest Sites. Additionally, the connection between the parameter determination system and finite element analysis is discussed, where the parameters for the Modified Cam Clay model are evaluated. The framework is valuable in the early stages of projects, providing detailed soil information when soil data is limited. Ongoing research aims to assess the accuracy of the derived soil and constitutive model parameters and to expand the system’s capabilities by including additional in-situ tests.

Suitability mapping for alternative crops: A consistent, high-resolution approach for the United States

Alternative crops are a key aspect of many nature-based solutions in agriculture, and there is a need for more consistent geographic information on biophysical suitability to aid in both farm-level planning and larger-scale analyses. Here we describe an approach for generating consistent, replicable, high-resolution suitability maps for any alternative crop species across the USA. The method employs a criteria-based approach to map potential species performance using a simple suitability index. Criteria for suitable and ideal ranges of values for influential biophysical variables are created using data collected from published sources and are reviewed by experts. Publicly available soil and climate map data are used with the criteria to map suitability for each variable which are integrated into an overall suitability index map. Maps of unsuitable locations are combined to produce a limiting variable map showing which category of environmental variables is most limiting. We demonstrate the application of this approach for two alternative perennial crops, apple (Malus spp.) and Chinese chestnut (Castanea mollissima) and validate its accuracy using known farm locations. Maps of apple and chestnut in four distant study regions show varying patterns of suitability and potential performance depending on the climate and geophysical characteristics of the region. The maps can be used to identify areas of high suitability and compare across regions or between species and be combined with socio-economic and environmental datasets for further analysis. Compared to other approaches, ours can be applied to multiple species with a range of pre-existing knowledge in a consistent way, allowing for reliable mapping and subsequent research and planning for alternative crops and nature-based solutions in agriculture.

Prediction of resilient modulus with pre-post experimental data of undisturbed subgrade soils using machine learning algorithms

The resilient modulus (MR) of subgrade, which shows relationship between stress and unit deformation of a pavement systems under traffic loads, is a design parameter of the pavement structure. Although a cyclic triaxial test apparatus can be used to directly determine the MR of the subgrade in the laboratory, utilizing prediction models based on easily obtainable soil parameters, is a more efficient method when taking time and cost considerations into account. A comprehensive laboratory testing program is designed to create MR prediction models using machine learning (ML) algorithms. 70 undisturbed soil samples are subjected to MR tests, as well as physical and engineering soil properties tests (water content, field density, specific gravity, gradation, consistency limits, unconfined compressive strength, swell pressure, swell percentage). Soil samples are drilled from a highway that has been in operation for over five years.First, a linear model like MLR is used in the study. Next, nonlinear regression models like RF, GBM, LightGBM, CatBoost, and XGBoost algorithms are used. Research findings showed that nonlinear regression models outperformed linear regression models in predicting the MR (R2 > 0.85), with the XGBoost algorithm yielding the best accuracy (R2 = 0.90). Apart from the primary effects such as confining pressure (σ3) and deviatoric stress (σd), it was found that unconfined compressive strength (qu), natural water content (wn), and swelling percentage (SR) are significant parameters in the prediction of MR among all parameters.

Towards data-driven tropical forest restoration: Uncovering spatial variation, interactions and historical management effects on nutrients along soil depth gradients

Data scarcity hinders global conservation initiatives, and there is a pressing demand for spatially detailed soil and species data to restore human-altered tropical forests. We, therefore, aimed to generate foundational soil environment and habitat suitability data and high-resolution soil maps to aid restoration efforts in a critical ecosystem of the threatened Indo-Burma Biodiversity Hotspot region, i.e., Tarap Hill Reserve (THR) in Bangladesh. Using multiple soil depths and vegetation data, we answered three major questions. (QI) How do spatial distribution and the relationships between soil physicochemical properties (i.e., pH, sand, silt, and clay percentages, organic carbon, and nutrients – N, P, K, Ca, Mg, Fe, and Zn) vary from surface to deeper soils (top 1 m)? (QII) How do different forest management interventions, i.e., old-growth forests (OGF), mixed plantations (MXP), and mono-specific plantations (MOP), influence soil properties, nutrients, and carbon in different soil depths? (QIII) Which spatial interpolation methods are best suited for making more accurate soil property predictions at different depths? Our analyses reveal decreasing availability of critical nutrients like N, P, Mg, and Fe from surface to subsurface soils, while pH, soil organic carbon, and clay content increased with depth. Several soil properties showed significant interactions, although the strength of the interactions changed from surface to deeper soils. Besides, forest management interventions significantly influenced soil functionality by having higher nutrient availability and soil organic carbon in OGF than MXP and MOP. Predictive performances of the deterministic and geostatistical interpolation methods varied for different soil properties in different soil depths, and soil maps revealed substantial heterogeneity in the distribution of soil properties across space and along depths. This study represents a pioneering step in data-driven tropical forest restoration, and our novel findings and high-resolution soil maps could guide future studies focusing on species habitat preferences, restoration ecology, and spatial conservation planning in the Indo-Burma Biodiversity Hotspot region and elsewhere in the tropics.

Advance deep learning for soil type classification in space informatics

Accurate soil type categorization is very important for resource management in space exploration. Using a complete system including a space station, rovers, and a deep learning framework, this study proposes an advanced deep learning model for soil type categorization in space informatics. Gathering and preprocessing multispectral and hyperspectral soil data, the rovers send it to the space station for in-depth study. Our model had a test accuracy of about 80%. For space informatics, the suggested method guarantees strong and accurate soil categorization, therefore enabling efficient decision-making.

CHARACTERIZATION OF RUNOFF ON AGRICULTURAL SOILS IN THE BANDAMA BLANC WATER-SHED, NORTHERN IVORY COAST, USING THE SCS-CN METHOD WITH GEOGRAPHIC INFOR-MATION SYSTEM (GIS) TOOLS

This study focused on the characterization of runoff on agricultural soils in theBandama Blanc watershed in Badikaha, Northern Cote dIvoire. The objective was to highlight the influence of land use change on runoff. To achieve this, soil data and profiles were utilized, allowing for the analysis of the hydrological properties and characteristics of the soils in the study area using the SCS (U.S.D.A.) method. The study revealed a continuous increase in the proportions of built-up/bare soil and cultivated areas over three study periods. The respective proportions were 16%, 27%, and 48% for built-up/bare soil, and 11%, 17%, and 33% for cultivated areas in the years 1986, 2004, and 2023. Additionally, it showed that the soils in the watershed predominantly exhibit clayey texture. These findings, combined with curve numbers (CN), highlighted significant runoff occurring in the study area, with average CN values of 70.57, 57.14, and 66.67 for 1986, 2004, and 2023, respectively. It follows from these results that runoff is more pronounced in urban areas, bare soils, highly mechanized agricultural environments, and watercourses. This study demonstrated that GIS and remote sensing techniques enable large-scale determination of runoff using the SCS-CN method. Furthermore, it serves as a simple and cost-effective tool for modeling runoff.

Soil Nutrient Analysis and Automatic Monitoring in Precision Agriculture

ABSTRACT The higher productivity from soil can be achieved through Wireless Sensor Networks (WSNs) technology; for this reason, the implementation of WSNs in precision agriculture is increasing day by day. Among the different technologies for crop monitoring, WSNs are recognized as a powerful option for collecting and processing data in the agricultural domain, with low cost and low energy consumption. The ultimate aim of this paper is to predict the precise values of soil nutrients nitrogen, phosphorus, and potassium (NPK) using a machine learning (ML)-based mathematical model formulation. The proposed system will use Global System for Mobile Communications (GSM) technology to automatically monitor soil parameters. It transfers soil data over the mobile network using a GSM modem. In the hardware part, sensor node units were developed to fetch and load data through the energy-efficient GSM, utilizing a bi-directional multi-level text messaging option to improve the alarm system’s efficiency. The system contains sensors such as potential of hydrogen and humidity (PH), which are used to monitor soil data collected from the sensors by the microcontroller. Additionally, as a novel contribution, machine learning based on regression models is applied to the NPK data. A novel data interpolation approach is proposed for data oversampling. The R2 values are compared, achieving nearly 99.5% accuracy in all cases. This paper focuses on various challenges and scalability issues encountered in research and discusses different results obtained by monitoring various soil parameters in a real-time agricultural environment.

CHARACTERIZATION AND CLASSIFICATION OF SOILS DEVELOPED ON COASTAL PLAIN SOILS FOR CROP PRODUCTION IN ORON LGA, SOUTH- SOUTH, NIGERIA

Soils are characterized and classified based on its unique properties. Detailed characterization of four representative areas of Oron coastal plain soils in South –South, Nigeria was carried out. Soil samples were collected from pedogenic horizons of soils in four sampling sites. Routine analysis of soil properties was carried out in the laboratory with standard laboratory procedures. Soil data was subjected to descriptive statistics using statistical analytical system. The soils have a deep well drafted profile of about deep 200 cm. The soil texture varied in areas ranging from loamy sand to sandy loam, sandy and sandy clay loam while bulk density increased down the natural horizons. The pH varied between moderately acidic to strongly acidic in the soils of the study area. The morphology of soils ranged in various colour matrix of hues (10-7.5) and Chroma values (1-8) in all horizons. The soils were characterized by Dark Brown (10YR3/3), Dark Greyish Brown (10YR4/2) and Yellowish Brown (10YR 5/4) to Grey (7.5YR6/2). The soils had low concentrations of exchangeable cations (Ca, Mg, Na and K). The Coefficient of variation (CV%) values ranged from 0.74 to 91.6 in Ca, Mg, Na and K. All the parameters in the soils of the study area showed low and medium mean values except soils of Esin Ufot1 and 2 which showed high mean values of Na with Esin Ufot 2 having the highest mean value of sodium to be 0.18 Cmol/kg. Suborder soils were classified as Grossarenic Kandiaqualfs (CEC > 16 Cmol/kg) for Esin Ufot1.Esin Ufot2, Esuk Oron1 while Esuk Oron 2 were classified as Typic Kandaquults (CEC < 16 Cmol/kg). A great importance in providing adequate data to enable right decision taking in the choice of site for developmental projects and crop production.

Comparison of cation exchange capacity extraction methods for soil data harmonization and soil classification in Central and East Europe

Cation exchange capacity and base saturation are of crucial importance for soil characterisation and classification; however, the interchangeability of soil data for international assessment of soil productivity, soil classification, mapping, and modelling is limited due to the lacking comparisons between results obtained using different analytical methods in particular regions of the world. The aim of the present study was to analyse the relationships between cation exchange capacity and base saturation measured using the methods adopted in Central and East Europe, and ‘standard’ techniques required for soil classification suggested by World Reference Base (WRB). This study was carried out using 183 soil samples collected from Luvisols, Retisols, Planosols, Chernozems, Phaeozems, Cambisols, and Arenosols in Poland, representing a wide range of texture, pH, and organic carbon content. A close comparability was found in noncalcareous soils between the ‘total sorption capacity’ (T) measured in Central and East Europe as the sum of base cations and ‘total’ (‘hydrolytic’) acidity, with the ‘standard’ cation exchange capacity (CEC) measured using 1 M ammonium acetate buffered at pH 7. The close correlation between T and CEC values (in noncalcareous soils) facilitates reliable data recalculation and its application in global modelling, soil classification and mapping. For soils containing carbonates, CEC must be measured using reference methods, because no relationship exists between T and CEC. The ‘potential’ base saturation (V) derived on the basis of T may be reliably recalculated to ‘standard’ base saturation (BS), allowing a retrieval of archival data from Central and East European regional databases and published reports. Similarities between the values of cation exchange capacity and base saturation, whether measured or calculated using the local and standard methods, allow a positive verification of previously proposed correlations between the local soil taxa and the reference soil groups of the WRB classification and soil orders defined by USDA Soil Taxonomy. The pH values corresponding to 50 % of ‘standard’, ‘potential’, and ‘effective’ base saturation were estimated at 5.5, 5.2, and 4.8, respectively. Irrespective of the differences between current estimates and previously reported pH threshold values corresponding to 50 % base saturation, the obtained results confirm that field measurements of soil pH may be considered a substitute for laboratory-measured base saturation for some purposes, such as soil classification.

Two Years of Cotton (Gossypium hirsutum L.) Data from the Georgia Coastal Plain, USA

The sustainable management of Earth’s complex ecosystems requires an abundance of field data to support long term stewardship. Remotely sensed satellite data provide crucial supplements to field measurements and are essential for deriving key operational products for monitoring Earth systems. However, to accurately calibrate and validate the models used to develop monitoring datasets, coincident field measurements are required. In 2018 and 2019, data related to cotton (Gossypium hirsutum L.) crops were collected from five fields in two farms located in Georgia, USA. Collections were timed to coincide with satellite overpasses to support the development of remote sensing-based crop and soil data products. Data collected include soil moisture, plant water content, above ground biomass, crop height, plant phenology, and field management practices (row direction, row spacing, and plant density). The datasets include 512 records collected in 2018 and 303 records collected in 2019. The data are archived in the National Agricultural Library Ag Data Commons repository and are available for use by researchers seeking crop and soil validation data.

A global dataset of gross nitrogen transformation rates across terrestrial ecosystems

Rates of nitrogen transformations support quantitative descriptions and predictive understanding of the complex nitrogen cycle, but measuring these rates is expensive and not readily available to researchers. Here, we compiled a dataset of gross nitrogen transformation rates (GNTR) of mineralization, nitrification, ammonium immobilization, nitrate immobilization, and dissimilatory nitrate reduction to ammonium in terrestrial ecosystems. Data were extracted from 331 studies published from 1984–2022, covering 581 sites. Globally, 1552 observations were appended with standardized soil, vegetation, and climate data (49 variables in total) potentially contributing to the observed variations of GNTR. We used machine learning-based data imputation to fill in partially missing GNTR, which improved statistical relationships between theoretically correlated processes. The dataset is currently the most comprehensive overview of terrestrial ecosystem GNTR and serves as a global synthesis of the extent and variability of GNTR across a wide range of environmental conditions. Future research can utilize the dataset to identify measurement gaps with respect to climate, soil, and ecosystem types, delineate GNTR for certain ecoregions, and help validate process-based models.

Mapping Field-Level Maize Yields in Ethiopian Smallholder Systems Using Sentinel-2 Imagery

Remote sensing offers a low-cost method for estimating yields at large spatio-temporal scales. Here, we examined the ability of Sentinel-2 satellite imagery to map field-level maize yields across smallholder farms in two regions in Oromia district, Ethiopia. We evaluated how effectively different indices, the MTCI, GCVI, and NDVI, and different models, linear regression and random forest regression, can be used to map field-level yields. We also examined if models improved by adding weather and soil data and how generalizable our models were if trained in one region and applied to another region, where no data were used for model calibration. We found that random forest regression models that used monthly MTCI composites led to the highest yield prediction accuracies (R2 up to 0.63), particularly when using only localized data for training the model. These models were not very generalizable, especially when applied to regions that had significant haze remaining in the imagery. We also found that adding soil and weather data did little to improve model fit. Our results highlight the ability of Sentinel-2 imagery to map field-level yields in smallholder systems, though accuracies are limited in regions with high cloud cover and haze.

Spatial variations of annual net ecosystem productivity and its trend over Chinese terrestrial ecosystems based on spatial downscaling.

Annual net ecosystem productivity (NEP), the amount of net carbon sequestration during a year, serves as the basis of terrestrial carbon sink. Quantifying the spatial variations of NEP and its trend would enhance our understandings on the response and adaption of ecosystems to environmental change, which also serves for the regional carbon management targeting at carbon neutrality. Based on process-based model and data-driven model simulating NEP, we selected the optimal simulating NEP mostly representing NEP spatial variations with multiple site eddy covariance measurements to develop the spatial downscaling method and generate high resolution NEP data of China, which was used to examine the spatial variations of NEP and its trend and driving factors during 2000-2017. Compared with process-based model results, data-driven model simulating NEP could mostly represent the spatial variation of site measurements. The random forest regression based on climate, soil, and biological data combining with the simple scaling could successfully downscale NEP to a high spatial resolution. From 2000 to 2017, the total amount of NEP in China was (1.30±0.03) Pg C·a-1, showing a decreasing-increasing pattern with the inflection point in 2009. Chinese NEP decreased from southeast to northwest, showing a descending latitudinal distribution and an ascending longitudinal distribution, with the combined effects of climate and biotic factors. NEP trend decreased from east towards west, which was only accompanied with a slightly ascending longitudinal distribution, while photosynthetically active radiation and soil organic carbon content dominated the spatial variations of NEP trend. Therefore, the spatial patterns of generated NEP obviously differed from those of NEP trend, suggesting the obvious difference between the responses and adaptions of ecosystems to environmental changes.

Using a Triple Sensor Collocation Approach to Evaluate Small-Holder Irrigation Scheme Performances in Northern Ethiopia

This study uses a triple-sensor collocation approach to evaluate the performance of small-holder irrigation schemes in the Zamra catchment of Northern Ethiopia. Crop water productivity (CWP), as an integrator of biomass production and water use, was used to compare the overall efficiencies of three types of irrigation systems: traditional and modern diversions, and dam-based irrigation water supply. Farmer-reported data often rely on observations, which can introduce human estimation and measurement errors. As a result, the evaluation of irrigation scheme performance has frequently been insufficient to fully explain crop water productivity. To overcome the challenges of using one single estimation method, we used a triple-sensor collocation approach to evaluate the efficiency of three small-scale irrigation schemes, using water productivity as an indicator. It employed three independent methods: remotely sensed data, a model-based approach, and farmer in-situ estimates to assess crop yields and water consumption. To implement the triple collocation appraisal, we first applied three independent evaluation methods, i.e., remotely sensed, model-based, and farmer in-situ estimates of crop yields and water consumption, to assess the crop water productivities of the systems. Triple-sensor collocation allows for the appraisal and comparison of estimation errors of measurement sensor systems, and enables the ranking of the estimators by their quality to represent the de-facto unknown true value, in our case: crop yields, water use, and its ratio CWP, in small-holder irrigated agriculture. The study entailed four main components: (1) collecting in-situ information and data from small-holder farmers on crop yields and water use; (2) derivation of remote sensing-based CWP from the FAO WaPOR open database and time series; (3) evaluation of biomass, crop yields and water use (evapotranspiration) using the AquaCrop model, integrating climate, soil data, and irrigation management practices; (4) performing and analysis of a categorical triple collocation analysis of the independent estimator data and performance ranking of the three sensing and small-holder irrigation systems. Maize and vegetables were used as main crops during three consecutive irrigation seasons (2017/18, 2018/19, 2019/20). Civil war prevented further field surveying, in-situ research, and data collection. The results indicate that remote sensing products are performed best in the modern and dam irrigation schemes for maize. For vegetables, AquaCrop performed best in the dam irrigation scheme.