1
ABSTRACT The prediction of crop yield is of significant interest for growers utilising biochar on land, while managers prioritise the enhancement of soil organic carbon (SOC). However, it remains unclear to what extent machine learning can accurately predict crop yield or SOC when biochar is applied to soil. In this study, Random Forest (RF) and Multilayer Perceptron Neural Network (MLP‐NN) models were employed to predict crop yield and SOC with 297 paired data from field trials. The results indicated that the RF model (test R 2 = 0.83) did not differ significantly from the MLP‐NN model (test R 2 = 0.84) in predicting crop yield. However, the RF model (test R 2 = 0.87) performs significantly better than the MLP‐NN model (test R 2 = 0.53) in predicting SOC. The most influential features for crop yield were found to be the biochar application rate (15%), initial SOC (13%), biochar pH (10%), and biochar TP (10%). In contrast, the variation of SOC was primarily influenced by latitude (26%), biochar application rate (22%), initial SOC (15%), and biochar pH (13%). Furthermore, both crop yield and SOC variation were influenced by multiple factors, not solely one, and their impacts were not necessarily linear. This study suggests that the optimization of biochar pH and phosphorus content, along with the regulation of its application rate in sandy or clay‐rich soils, can simultaneously enhance both crop yield and SOC. In the future, we hope to develop a decision support system with prediction, different scenarios, and consultation capabilities based on geospatial location.
Biochar's impact on carbon sequestration and yield-scaled global warming potential in China: A machine learning-enhanced meta-analysis
Biochar's impact on carbon sequestration and yield-scaled global warming potential in China: A machine learning-enhanced meta-analysis
Read more115Developing machine learning models with multi-source environmental data to predict wheat yield in China
Developing machine learning models with multi-source environmental data to predict wheat yield in China
32Persistent effects of biochar on soil organic carbon mineralization and resistant carbon pool in upland red soil, China
Biochar as a soil ameliorant has generated great interest for scientists in improving soil quality and carbon sequestration. The objective of this study was to investigate the persistent effects of biochar application on soil organic carbon (SOC) mineralization and soil-resistant carbon (Cr) in upland red soil. This experiment was conducted from September 2011 to May 2016. Biochar was applied only once in September 2011 at rates of 0, 2.5, 5, 10, 20, 30 and 40 t/ha in the field experiment, designated as treatments B0, B1, B2, B3, B4, B5 and B6. The chemical properties, dynamics of SOC mineralization and soil-resistant carbon (Cr) were measured at the 1st and 6th year after biochar application. The results were as follows: biochar application at rates of 30 and 40 t/ha (B5 and B6 treatments) distinctly increased soil pH value and available P relative to B0 in 2011. The pH value, available P, SOC, total N and C/N ratio in B4, B5 and B6 treatments were significantly higher compared with the B0 treatment, where the B6 treatment increased the pH value by 0.80 and C/N ratio by 3.88 while increasing available P, SOC and total N by 24.18, 76.29 and 19.78%, respectively, compared with the B0 treatment in 2016. The cumulative SOC mineralization (Cm) occupied around 4.62–6.91% of total organic carbon (Ct), which showed a declining trend in 2016 as compared to 2011. The Cm/Ct ratio also showed a declining trend with biochar amendment at both samplings. The Cr occupied around 26–46% of SOC and showed obviously increasing trends both in 2011 and 2016. We further found that Cm/Ct showed highly significant (p < 0.01) negative correlations with the rates of biochar application both in 2011 and 2016. The Cr, however, showed very significant (p < 0.01) positive correlations with the rates of biochar application both in 2011 and 2016. This study suggested that biochar application to upland red soil persistently improved soil properties and resistant carbon. Cumulative SOC mineralization was clearly restrained by biochar amendment. This study can provide scientific support for improving soil fertility and enhancing carbon sequestration by application of large amount of biochar (40 t/ha) in upland red soil.
Read more1Investigations on temporal and spatial variation of slope-scale SOC erosion and deposition
Investigations on temporal and spatial variation of slope-scale SOC erosion and deposition
69Initial soil organic carbon stocks govern changes in soil carbon: Reality or artifact?
Changes in soil organic carbon (SOC) storage have the potential to affect global climate; hence identifying environments with a high capacity to gain or lose SOC is of broad interest. Many cross‐site studies have found that SOC‐poor soils tend to gain or retain carbon more readily than SOC‐rich soils. While this pattern may partly reflect reality, here we argue that it can also be created by a pair of statistical artifacts. First, soils that appear SOC‐poor purely due to random variation will tend to yield more moderate SOC estimates upon resampling and hence will appear to accrue or retain more SOC than SOC‐rich soils. This phenomenon is an example of regression to the mean. Second, normalized metrics of SOC change—such as relative rates and response ratios—will by definition show larger changes in SOC at lower initial SOC levels, even when the absolute change in SOC does not depend on initial SOC. These two artifacts create an exaggerated impression that initial SOC stocks are a major control on SOC dynamics. To address this problem, we recommend applying statistical corrections to eliminate the effect of regression to the mean, and avoiding normalized metrics when testing relationships between SOC change and initial SOC. Careful consideration of these issues in future cross‐site studies will support clearer scientific inference that can better inform environmental management.
Read moreLong-term effects of different organic resource rates, quality and nitrogen fertilizer on SOC development and conversion efficiency across Kenya.&#160;
&lt;p&gt;Maize monoculture with low external inputs, as frequently practiced in sub-Saharan Africa, usually leads to the long-term loss of soil fertility. This threatens the already poor yields in the region. Practices that add organic and mineral resources to the soil therefore promise to counteract soil fertility loss by providing the potential feed-stock for microbes to build new soil organic matter. We studied the effect of organic and mineral resource addition from five organic amendment types of different quality (relative N, lignin and polyphenol contents) and quantity and from chemical nitrogen fertilizer, on soil organic carbon (SOC) and soil nitrogen in the 15 cm topsoil of four long-term trials in contrasted sites in Kenya. They had different climate and soil texture and lasted between 16 and 19 years. Treatments were identical among sites, the organic resources were &lt;em&gt;Tithonia diversifolia&lt;/em&gt; (high quality and fast turnover) and &lt;em&gt;Calliandra calothyrsus&lt;/em&gt; (high quality and slow turnover), stover of &lt;em&gt;Zea mays&lt;/em&gt; (low quality and fast turnover), sawdust from &lt;em&gt;Grevillea robusta&lt;/em&gt; trees (low quality and slow turnover) and locally available farmyard manure (undefined quality and slow turnover). The organic resources were added in the quantities of 1.2 and 4 t C ha&lt;sup&gt;-1&lt;/sup&gt; yr&lt;sup&gt;-1&lt;/sup&gt; and the experiments included a split-plot treatment of &amp;#177;N addition (120 kg ha&lt;sup&gt;-1&lt;/sup&gt; in each of the two growing seasons per year).&lt;/p&gt;&lt;p&gt;Despite site-specific differences, the general trend across sites indicated that SOC is usually lost with all treatments. Typical losses ranged from 1.9% to 0.6% loss of initial SOC yr&lt;sup&gt;-1&lt;/sup&gt; for the control and the farmyard manure (at 4t C ha&lt;sup&gt;-1&lt;/sup&gt; year&lt;sup&gt;-1&lt;/sup&gt;) respectively. Adding &lt;em&gt;Calliandra&lt;/em&gt; or &lt;em&gt;Tithonia&lt;/em&gt; at 4t C ha&lt;sup&gt;-1&lt;/sup&gt; yr&lt;sup&gt;-1&lt;/sup&gt; also enable to slow the loss (about 1.1% of initial SOC yr&lt;sup&gt;-1&lt;/sup&gt; lost). Nevertheless, the addition of 4t C ha&lt;sup&gt;-1&lt;/sup&gt; yr&lt;sup&gt;-1&lt;/sup&gt; farmyard manure and &lt;em&gt;Calliandra calothyrsus&lt;/em&gt;, together with mineral N addition, achieved a gain in SOC over time only in the site which had lowest initial SOC contents (about 6 g C kg&lt;sup&gt;-1&lt;/sup&gt;), a sand of 31% content and a climate that was suitable for maize growth. In contrast, another site with low initial SOC content, high sand content, but a less suitable climate, with frequent failures of the maize crop, lost SOC in all treatments. In the site with initially 25 g C kg&lt;sup&gt;-1&lt;/sup&gt;, the farmyard manure treatment at 4t C ha&lt;sup&gt;-1&lt;/sup&gt; yr&lt;sup&gt;-1&lt;/sup&gt; with N addition was the only treatment that could maintain SOC, while in the site with initially highest SOC (about 30 g C kg&lt;sup&gt;-1&lt;/sup&gt;), all treatments lost SOC. The mineral N addition, with the exception of two treatments in the lowest fertility site, had no significant effect on the response of SOC to the different organic resource treatments. Our results indicate that farmyard manure may be the most suitable resource to reduce losses of SOC, but increases may only be possible in sites with initially low SOC contents, e.g. where, because of sufficiently long cultivation activities, a new steady state with low SOC contents has already been attained.&lt;/p&gt;
Read more3Soil bacterial habitat generalists strengthen depth-dependent organic carbon accrual in coastal reclaimed lands after afforestation
Soil bacterial habitat generalists strengthen depth-dependent organic carbon accrual in coastal reclaimed lands after afforestation
Read moreImpacts of inorganic and organic fertilization on soil organic carbon and crop production: a meta-analysis
Impacts of inorganic and organic fertilization on soil organic carbon and crop production: a meta-analysis
Fertilizer or pollutant: analyzing the effects of biochar on soil organisms using machine learning
In the context of carbon neutrality targets, biochar is widely promoted as a soil amendment to sequester organic carbon in soils. Although a wealth of research has illustrated the benefits of biochar to plants, its potential toxicity to soil fauna and microbes requires serious consideration. The aim of this study was to perform a meta-analysis of experimental data on biochar effects (i.e. percentage change in endpoints after biochar application compared to the control group) on plants, animals, and microorganisms. The experimental data were extracted from 61 papers and consists of 1329 data points. In a next step, machine learning was used to develop a classifier to predict, whether biochar has positive or negative consequences on soil organisms based on biochar and soil properties. The meta-analysis shows that the effect of biochar is negatively correlated with the biochar application rate, biochar pH, pyrolysis temperature, and soil pH. A random forest classifier was then developed to classify whether biochar was “beneficial” or “hazardous” based on four types of descriptors: biochar properties, soil properties, test organism, and endpoint type. The accuracy of the best model achieved an R 2 of 0.79. In the next step, a quantitative model was developed to predict the effect with an R 2 of 0.48. The model is of great significance for understanding the role of biochar in soil and improving the quality control strategy for biochar production. Graphical Abstract
Read more4Chapter 34 - Digital soil mapping of organic carbon at two depths in loess hilly region of Northern Iran
Chapter 34 - Digital soil mapping of organic carbon at two depths in loess hilly region of Northern Iran
27Estimating spatially distributed SOC sequestration potentials of sustainable land management practices in Ethiopia
The sustainable land management program (SLMP) of Ethiopia aims to improve livelihoods and create resilient communities and landscape to climate change. Soil organic carbon (SOC) sequestration is one of the key co-benefits of the SLMP. The objective of this study was to estimate the spatial dynamics of SOC in 2010 and 2018 (before and after SLMP) and identify the SOC sequestration hotspots at landscape scale in four selected SLMP watersheds in the Ethiopian highlands. The specific objectives were to: 1) comparatively evaluate SOC sequestration estimation model building strategies using either a single watershed, a combined dataset from all watersheds, and leave-one-watershed-out using Random Forest (RF) model; 2) map SOC stock of 2010 and 2018 to estimate amount of SOC sequestration and potential; 3) evaluate the impacts of SLM practices on SOC in four SLMP watersheds. A total of 397 auger composite samples from the topsoil (0–20 cm depth) were collected in 2010, and the same number of samples were collected from the same locations in 2018. We used simple statistics to assess the SOC change between the two periods, and machine learning models to predict SOC stock spatially. The study showed that statistically significant variation (P < 0.05) of SOC was observed between the two years in two watersheds (Gafera and Adi Tsegora) whereas the differences were not significant in the other two watersheds (Yesir and Azugashuba). Comparative analysis of model-setups shows that a combined dataset from all the four watersheds to train and test RF outperform the other two strategies (a single watershed alone and a leave-one-watershed-out to train and test RF) during the testing dataset. Thus, this approach was used to predict SOC stock before (2010) and after (2018) land management interventions and to derive the SOC sequestration maps. We estimated the sequestrated, achievable and target level of SOC stock spatially in the four watersheds. We assessed the impact of SLM practices, specifically bunds, terraces, biological and various forms of tillage practices on SOC using partial dependency algorithms of prediction models. No tillage (NT) increased SOC in all watersheds. The combination of physical and biological interventions (“bunds + vegetations” or “terraces + vegetations”) resulted in the highest SOC stock, followed by the biological intervention. The achievable SOC stock analysis showed that further SOC stock sequestration of up to 13.7 Mg C ha--1 may be possible in the Adi Tsegora, 15.8 Mg C ha-1 in Gafera, 33.2 Mg C ha-1 in Azuga suba and 34.7 Mg C ha-1 in Yesir watersheds.
Read more23Carbon sequestration potential and its main drivers in soils under alfalfa (Medicago sativa L.)
Carbon sequestration potential and its main drivers in soils under alfalfa (Medicago sativa L.)
Effects of fresh-salt water interaction on spatial variations of soil organic carbon in reed wetland of Yellow River Estuary.
Estuarine wetlands exhibit significant interaction between fresh and salt water, with long-term carbon sequestration capability. We set up 60 sampling sites in the reed wetlands of the fresh-salt water interaction zone of the Yellow River Estuary, covering four different zones of the weak-intensity fresh-salt water interaction zone (WIZ), medium-intensity fresh-salt water interaction zone (MIZ), high-intensity interaction fresh-salt water zone (HIZ) and strong-intensity fresh-salt water interaction zone (SIZ). We investigated how fresh-salt water interaction affected the spatial variation of soil organic carbon (SOC) storage. The results showed that the area of reed wetland accounted for 17.8% of the total area of the fresh-salt water interaction zone the Yellow River Estuary, which mainly distributed in the WIZ and MIZ. The SOC content of reed wetland in the fresh-salt water interaction zone ranged from 1.09 to 3.65 g·kg-1, the SOC density was between 1.85-5.84 kg·m-2, and the SOC storage was (17.32±3.64)×104 t. The SOC content and SOC density decreased with increasing fresh-salt water interaction. There were significant differences in surface SOC content between different subzones of the fresh-salt water interaction zone. The surface SOC content decreased significantly with the increases of fresh-salt water interaction intensity. SOC density was positively correlated with SOC, TN, NH4+-N, and biomass, but negatively correlated with salt ions, soil bulk density, pH, and EC. SOC storage in the 0-30 cm soil layer accounted for 50.9%-64.2% of that in the 0-60 cm soil layer, while SOC storage in the 0-60 cm soil layer occupied 19.1%-37.7% of that in the 0-400 cm soil layer. The results could provide a scientific basis for accurately evaluating SOC storage of estuarine wetlands, improving carbon sink function and wetland management.
Read more8Sustainable effects of nitrogen reduction combined with biochar on enhancing maize productivity and nitrogen utilization
Sustainable effects of nitrogen reduction combined with biochar on enhancing maize productivity and nitrogen utilization
57Assessment of climate change impacts on soil organic carbon and crop yield based on long-term fertilization applications in Loess Plateau, China
Climate change may significantly impact crop yields and soil. In this study the DNDC model, together with climatic outputs from Hadley Centre’s general circulation model (HadCM3), was used to investigate the influence of projected climate change and management practices on soil organic carbon (SOC) dynamics and crop yield of the Chinese Loess Plateau. The results identify management practices with the greatest potential to mitigate climate change and to increase SOC in this area. Field experiments on winter-wheat (Triticum aestivum L.) and summer maize (Zea mays L.) rotation included a control and four types of fertilization treatments: T1 (control), T2 (inorganic fertilizer), T3 (NPK inorganic fertilization combined with wheat or maize residue return), T4 (NPK inorganic fertilization combined with low amount of manure) and T5 (NPK inorganic fertilization combined with high amount of manure). DNDC model was calibrated using the field data from 1991 to 2000 and validated from 2001 to 2010. Furthermore, a baseline climate and three future climate scenarios (A1B, A2 and B1) were considered. DNDC model effectively simulated the SOC and crop yields. The findings showed that in 1991–2010, T1 maintained its initial SOC level but reduced crop yields, while T2 promoted crop production with less effect on soil carbon storage. However, T3, T4 and T5 enhanced both crop yield and soil carbon, and the best results were observed under T5. The investigated climate scenarios substantially affect SOC content and crop yields. In terms of SOC content, B1 had great effects on T1, T4 and T5, while A1B on T2 and T3. Considering crop yields, in all treatments, the trends are B1 > A1B > A2 for winter-wheat and A2 > A1B > B1 for summer maize, respectively. The impacts of climate changes on SOC dynamics and crop yields were different depending on the management applied. Thus, the adoption of certain management practices in the Chinese Loess Plateau agroecosystems could be critical in maximizing SOC sequestration and reducing CO2 in the atmosphere. Reasonably low temperature and high precipitation can enhance winter-wheat yields, while maize yields need medium temperature and precipitation. We recommended the combined application of inorganic and organic fertilizers to achieve a balance between food security and soil carbon sequestration objectives.
Read more
Copyright 2026 Cactus Communications. All rights reserved.
