Search Results (48)

Heavy metal-contaminated soil poses a severe threat to environmental quality and human health, calling for eco-friendly and efficient remediation strategies. This study explored the use of biochar-immobilized copper-resistant Pseudomonas aeruginosa to remediate copper-contaminated soil and promote growth of Chinese milk vetch (Astragalus sinicus L.). Indoor pot experiments compared four groups: copper-contaminated soil (control), soil with biochar, soil with free bacteria, and soil with biochar-immobilized bacteria (IM). Results showed IM had the most significant effects on soil properties: it raised pH to 7.04, reduced bioavailable copper by 34.37%, and increased catalase (3.48%) and urease (78.95%) activities. IM also altered soil bacterial communities, decreasing their richness and evenness (alpha diversity) while shifting community composition. For Chinese milk vetch, IM reduced leaf malondialdehyde (a marker of oxidative stress) by 15%, increased total dry weight by 90%, and lowered copper accumulation in roots (18.62%) and shoots (60.33%). As a nitrogen-fixing plant, the vetch’s nitrogen fixation in roots and shoots rose by 82.70% and 57.08%, respectively, under IM. These findings demonstrate that biochar-immobilized Pseudomonas aeruginosa is a promising in situ amendment for remediating copper-contaminated soil and boosting plant growth. Full article

Returning straw and green manure to the field is a vital agronomic practice for improving crop yields and ensuring food security. However, the existing research primarily focuses on drylands and low-fertility paddy fields. A systematic discussion of the yield-increasing mechanisms and soil response patterns of medium- and long-term organic fertilization in subtropical, high-organic-matter paddy fields is lacking. This study conducted a six-year field experiment (2019–2024) in a typical high-fertility rice production area, where the initial organic matter content of the 0–20 cm topsoil layer was 44.56 g kg⁻¹. Four treatments were established: PK (no nitrogen, only phosphorus and potassium fertilizer), NPK (conventional nitrogen, phosphorus, and potassium fertilizer), NPKM (NPK + full-amount winter milk vetch return), and NPKS (NPK + full-amount rice straw return). We collected 0–20 cm topsoil samples during key rice growth stages to monitor the dynamic changes in nitrate and ammonium nitrogen. The rice SPAD, LAI, plant height, and tiller number were also measured during the growth period. After the six-year rice harvest, we determined the properties of the topsoil, including its organic matter, pH, total nitrogen, phosphorus, potassium, available phosphorus and potassium, and alkali hydrolyzable nitrogen. The results showed that, compared to NPK, the organic matter content of the topsoil (0–20 cm) increased by 6.36% and 5.16% (annual average increase of 1.06% and 0.86%, lower than in low-fertility areas) in the NPKS and NPKM treatments, respectively; the total nitrogen, phosphorus, and potassium content increased by 16.59%, 8.81%, and 10.37% (NPKS) and 6.70%, 5.12%, and 11.62% (NPKM), respectively; the available phosphorus content increased by 21.87% and 8.42%, respectively; the available potassium content increased by 47.38% and 11.56%, respectively; and the alkali hydrolyzable nitrogen content increased by 3.24% and 2.34%, respectively. However, the pH decreased by 0.07 in the NPKS treatment while it increased by 0.17 in the NPKM treatment, respectively, compared to the PK treatment. NPKS and NPKM improved key rice growth indicators such as the SPAD, LAI, plant height, and tillering. In particular, the tillering of the NPKS treatment showed a sustained advantage at maturity, increasing by up to 13.64% compared to NPK, which also led to an increase in the effective panicle number. Compared to NPK, NPKS and NPKM increased the average yield by 9.52% and 8.83% over the six years, respectively, with NPKM having the highest yield in the first three years (2019–2021) and NPKS having the highest yield from the fourth year (2022–2024) onwards. These results confirm that inputting organic materials such as straw and green manure can improve soil fertility and rice productivity, even in rice systems with high organic matter levels. Future research should prioritize the long-term monitoring of carbon and nitrogen cycle dynamics and greenhouse gas emissions to comprehensively assess these practices’ sustainability. Full article

Mixed sowing of green manure in winter is a unique farming mode in southern China, which has the potential to replace or partially replace nitrogen fertilizer. To investigate how mixed sowing of green manure combined with nitrogen reduction regulates soil organic carbon and its fractions, this study was conducted in the 3/4 Chinese milk vetch × 1/4 rapeseed farming mode, without nitrogen fertilizer (CK), 100% N fertilizer (150 kg ha⁻¹, N1MR), 20% N fertilizer reduction (120 kg ha⁻¹, N2MR), 40% N fertilizer reduction (90 kg ha⁻¹, N3MR), and 60% N fertilizer reduction (60 kg ha⁻¹, N4MR). The main results were the N2MR treatment could guarantee stable and increased rice yield. The N1MR and N2MR treatments were more conducive to the accumulation of TOC. The N4MR and N2MR treatments were more conducive to the increase and accumulation of AOC and DOC. The effective spikes were positively correlated with TOC and ROC. The grain number per panicle was positively correlated with DOC. The seed-setting rate was positively correlated with ROC. Overall, mixed sowing of Chinese milk vetch and rapeseed combined with 20% nitrogen reduction ensures a stable yield and increase in rice. Nitrogen reduction by 60% and 20% is beneficial to the increase and accumulation of TOC, AOC, and DOC in soil. Full article

The co-incorporation of green manure and rice straw is commonly used to increase rice yield and improve soil fertility in paddy fields. However, the effects on nutrient uptake and utilization of rice under the synergistic interaction mechanism in the Taihu Plain of the Yangtze River Delta remain unclear. Based on field experiments, this study investigated the effects of green manure with rice straw return (GMS) under different nitrogen (N) fertilization rates on rice yield, nutrient use efficiency, and soil fertility. The results revealed that green manuring significantly increased rice yield while improving the uptakes and use efficiencies of N, phosphorus (P) and potassium (K). Green manure (GM) with 40% N fertilizer reduction (GM_N60) maintained the grain and straw yields and nutrient uptakes compared to winter fallow with 100% conventional N application (WF_N100). The N recovery efficiency in GM_N60 reached 45.52%, increasing by 41.26% compared to WF_N100. Rice yield and K uptake in the GMS with 40% N fertilizer reduction treatment (GMS_N60) was 10,058 and 15.41 kg/hm², increasing by 14.43% and 9.43% compared to winter fallow with rice straw return and 100% conventional N (WFS_N100). The N, P and K agronomic efficiencies in GMS_N60 increased by 77.04%, 50.22%, and 50.22% compared to WFS_N100, respectively. These findings indicate that rice straw return enhances the fertilizer-saving and yield-increasing effects of GM, promotes rice K uptake and improves P and K use efficiencies. The GM treatment increased the soil organic matter (SOM), total potassium (TK), ammonium nitrogen (NH₄⁺-N) and nitrate nitrogen (NO₃⁻-N) contents. Among the soil fertility indicators, TK and SOM were the most important factors influencing rice yield and N uptake. In conclusion, GMS can maintain or increase rice yield with 40% N fertilizer reduction, improve nutrient use efficiencies, and increase the reuse of rice straw, thereby supporting green and efficient rice production in the southern Jiangsu paddy area. Full article

To explore the characteristics of soil microbial community structure diversity for different planting patterns in paddy fields, and to screen out the planting patterns suitable for the promotion of double-cropping rice areas in the middle reaches of the Yangtze River, five typical planting patterns were set up in this study. The five patterns are Chinese milk vetch–early rice–late rice (CRR, CK), Chinese milk vetch–early rice–sweet potato || late soybean (CRI), rapeseed–early rice–late rice (RRR), rapeseed–early rice–sweet potato || late soybean (RRI) and potato–early rice–late rice (PRR). The variation characteristics of soil microbial community structure diversity and the correlation between soil environmental factors and soil microbial community structure diversity under the triple-cropping system in the double-cropping rice area of the middle reaches of the Yangtze River were studied by 16S rRNA high-throughput sequencing and real-time fluorescence quantitative polymerase chain reaction (PCR). The results showed that after two years of experiment, the pH values of each treatment increased, and the rapeseed–early rice–late rice (RRR) model performed better. The soil organic matter and total nitrogen content of the milk vetch–early rice–sweet potato || late soybean (CRI) model was the highest, which increased by 7.89~35.02% and 6.59~26.80% compared with other treatments. The content of soil available phosphorus and available potassium in the potato–early rice–late rice (PRR) model was higher than that in other treatments, which was increased by 29.48% and 126.49% compared with the control. The Chinese milk vetch–early rice–sweet potato || late soybean (CRI) and rapeseed–early rice–sweet potato || late soybean (RRI) models were beneficial to increasing soil nitrate nitrogen and ammonium nitrogen content. Chinese milk vetch–early rice–sweet potato || late soybean (CRI) and rapeseed–early rice–late rice (RRR) patterns were beneficial for improving the microbial diversity index. Proteobacteria, Chloroflexi, and Actinobacteria are the top three dominant phyla in terms of the relative abundance of soil bacteria, and the top three dominant fungi are Ascomycota, Basidiomycota, and Mucor. The Chinese milk vetch–early rice–sweet potato || late soybean (CRI) and rapeseed–early rice–sweet potato || late soybean (RRI) patterns increased the relative abundance of soil Actinobacteria and Ascomycota. The contents of ammonium nitrogen, total organic carbon, nitrate nitrogen, and available phosphorus were the main environmental factors affecting soil microbial community structure. The findings can provide references for screening out the planting patterns suitable for the promotion of double-cropping rice areas in the middle reaches of the Yangtze River. Full article

Soluble organic nitrogen (SON) plays a critical role in soil nitrogen cycling, yet the effects of Chinese milk vetch (CMV) application on the composition of SON within paddy soil profiles remains poorly understood. This study aimed to investigate the effects of varying CMV application rates on the composition and vertical distribution of SON in paddy soils, evaluating its potential implications for soil fertility and nitrogen leaching. A three-year field experiment was conducted in a subtropical rice cultivation system, employing four CMV application rates (0, 15,000, 30,000, and 45,000 kg ha⁻¹). Soil samples were collected from three depth layers (0–20 cm, 20–40 cm, and 40–60 cm) at the rice maturity stage, and SON components, including free amino acid nitrogen (FAA-N), amide nitrogen (A-N), and soluble protein nitrogen (SP-N), were analyzed. The results demonstrated that CMV application significantly enhanced SON content, particularly in the topsoil (0–20 cm), with a 49.87% increase under the 45,000 kg ha⁻¹ treatment. SON constituted over 50% of the total soluble nitrogen in the 0–60 cm layer, with FAA-N, A-N, and SP-N identified as the predominant components. CMV facilitated the accumulation of small-molecular SON (e.g., FAA-N and A-N) in deeper soil layers, with FAA-N content increasing by 79.13% in the 20–40 cm layer and A-N content increasing by 64.85% in the 40–60 cm layer under the 45,000 kg ha⁻¹ treatment. In contrast, high-molecular-weight SON (e.g., SP-N) primarily accumulated in the topsoil due to stronger adsorption, while small-molecular-weight SON exhibited greater mobility, thereby elevating the risk of nitrogen leaching. These findings highlight the need for optimized CMV application rates to balance soil fertility and environmental sustainability in rice cropping systems. Full article

The cultivation of Chinese milk vetch (CMV) during the winter fallow season and the return of rice straw are important practices for increasing the soil fertility of paddy fields in southern China. In order to provide data-based evidence for the scientific strategy of nitrogen (N) fertilizer reduction through the incorporation of rice straw and CMV, a three-year field trial was conducted. The treatments included the three N application rates of 0%, 60%, and 100% of the local conventional rate (165 kg ha⁻¹), with the incorporation of CMV alone (MN0, MN60, and MN100) or with both CMV and rice straw (SMN60 and SMN100). The rice grain yield, N uptake, and dynamic changes in inorganic N in the soil and surface water were determined for the period from 2019 to 2021. The results show that both the rice grain yield and plant N uptake of the MN60 and SMN60 treatments were not significantly different from those of the treatment with only conventional N application (N100). Although the SMN100 treatment significantly increased the uptakes of N in the aboveground part in the tillering and shooting stages compared with SMN60, no significant differences were found between the grain yields in 2021. Meanwhile, the SMN60 treatment significantly increased the soil microbial biomass N and NH₄⁺-N contents during the maturity stage in 2020 and 2021, respectively, compared with MN60. Furthermore, the SMN100 treatment resulted in higher NO₃⁻-N concentrations in the surface water at days 3 and 6 after transplantation in 2020 than those under SMN60. In conclusion, the incorporation of CMV and rice straw with an application rate of 60% of conventional N fertilizer is an essential approach to reducing the risk of N loss while maintaining rice grain yields in the Jianghan Plain of China. Full article

Addressing the pressing issue of global warming, sustainable rice cultivation strategies are crucial. Milk vetch (MV), a common green manure in paddies, has been shown to increase CH₄ emissions, necessitating effective mitigation. This two-year field experiment assessed the impact of applying calcium peroxide (CaO₂), widely used in wastewater treatment and soil remediation due to its oxygen-releasing properties, on CH₄ emissions in conventional paddy fields (chemical fertilizer-only) and MV-incorporated fields. The results revealed that in conventional paddy fields, CaO₂ application significantly reduced the average CH₄ emissions by 19% without affecting rice yield. Compared with chemical fertilizer alone, MV incorporation increased the average rice yield by 12% but significantly elevated CH₄ emissions. However, in paddy fields with MV incorporation, CaO₂ application significantly reduced CH₄ emissions by 19% while preserving the yield benefits of MV. Soil analyses indicated that MV incorporation led to increased soil carbon content and increased mcrA and pmoA gene copy numbers, with elevated mcrA gene copy numbers being primarily responsible for the promoted CH₄ emissions. CaO₂ application improved the soil redox potential, reducing mcrA gene copies and consequently mitigating CH₄ emissions. Overall, CaO₂ application can contribute to global efforts to reduce CH₄ emissions while supporting rice productivity. Full article

Chinese milk vetch (CMV), as a typical green manure in southern China, plays an important role in improving soil quality and partially substituting nitrogen chemical fertilizers for rice production. Accurately estimating the aboveground biomass (AGB) of CMV is crucial for quantifying the biological nitrogen fixation amount (BNFA) and assessing its viability as a nitrogen fertilizer alternative. However, the traditional estimation methods have low efficiency in field-scale evaluations. Recently, unmanned aerial vehicle (UAV) remote sensing technology has been widely adopted for AGB estimation. This study utilized UAV-based multispectral and RGB imagery to extract spectral (Sp), textural (Tex), and structural features (Str), comparing various feature combinations in AGB estimation for CMV. The results indicated that the fusion of spectral, textural, and structural features indicated optimal estimation performance across all feature combinations, resulting in R² values of 0.89 and 0.83 for model cross-validation and spatial transferability validation, respectively. The inclusion of textural and spectral features notably improved AGB estimation, indicated an increase of 0.15 and 0.14 in R² values for model cross-validation and spatial transferability validation, respectively, compared with relying on spectral features only. Estimation based exclusively on structural features resulted in R² values of 0.65 and 0.52 for model cross-validation and spatial transferability validation, respectively. The present study establishes a rapid and extensive approach to evaluate the BNFA of CMV at the full blooming stage utilizing the optimal AGB estimation model, which will provide an effective calculation method for chemical fertilizer reduction. Full article

The incorporation of rice straw (RS) and Chinese milk vetch (CMV) with reduced chemical fertilizers (CFs) is a viable solution to reduce the dependency on CF. However, limited research has been conducted to investigate the impact of CMV and RS with reduced CF on rice production. A field trial was conducted from 2018 to 2021 with six treatments: CK (no fertilizer), F100 (100% NPK fertilizer (CF)), MSF100 (100% CF+CMV and RS incorporation), MSF80 (80% CF+CMV+RS), MSF60 (60% CF+CMV+RS), and MSF40 (40% CF+CMV+RS). The results revealed that compared with the F100, the MSF80 treatment maintained a significantly higher mean grain yield over the four years, with an increase of 5.8~24.5%. MSF80 treatment also improved nitrogen (N), phosphorus (P), and potassium (K) use efficiencies, sustainable yield index, and partial factor productivity. Soil organic matter (SOM), total nitrogen (TN), ammonium N (NH₄⁺-N), nitrate N (NO₃⁻-N), available phosphorus (AP), and available potassium (AK) contents were significantly enhanced under MSF80 across different growth stages in both 2020 and 2021 seasons over F100. Pearson correlation analysis revealed a strong positive correlation among SOM, TN, NH₄⁺-N, AP, AK, and rice yield. Additionally, Partial Least Squares Path Modeling (PLS-PM) demonstrated significant relationships between organic amendments, soil nutrients, nutrient uptake, and yield. The above findings suggest that combining RS returning with CMV incorporation is a long-term sustainable strategy for maintaining soil health, and it could reduce fertilizer addition by 20% without prejudicing rice grain yield under a rice-green manure rotation system. Full article

The winter planting of green manure (GM) is widely used in South China to reduce chemical nitrogen (N) fertilizer use, improve soil fertility, and maintain rice yields, but its effect on N runoff loss in paddy fields remains unclear. This study combines multi-site field experiments with a process model (WHCNS-Rice) to assess how GM with reduced N fertilizer impacts N runoff loss and its forms in the Yangtze River’s middle and lower reaches, considering different rainfall years. The network field experiments included four treatments: conventional fertilization (FR), conventional fertilization plus straw return (FRS), GM with a 40% N reduction (MR), and GM-straw combined return with a 40% N reduction (MRS). Monitoring the results showed that compared to the winter fallow treatment, the GM treatments reduced the peak and average total N (TN) concentrations by 11.1–57.9% (average 26.9%) and 17.1–27.3% (average 22.3%), respectively. The TN runoff loss under the GM treatment decreased by 3.50–10.61 kg N ha⁻¹ (22.5–42.1%). GM primarily reduced the runoff loss of dissolved inorganic N (DIN), with reductions at different sites ranging from 0.22 to 9.66 kg N ha⁻¹ (8.4–43.4%), indicating GM effectively decreases N runoff by reducing DIN. Model simulations of ponding water depth, runoff, TN concentration in surface water, and TN loss in paddy fields produced the consistency indices and simulation efficiencies of 0.738–0.985, 0.737–0.986, 0.912–0.986, and 0.674–0.972, respectively, indicating that the model can be used to evaluate water consumption and N runoff loss in the GM-paddy system. The simulations showed that GM with a 40% N fertilizer significantly reduced N runoff loss under all rainfall conditions, with the greatest reductions in wet years. Under wet, normal, and dry conditions, the GM treatments significantly reduced average TN loss by 0.37–5.53 kg N ha⁻¹ (12.77–29.17%), 0.21–5.32 kg N ha⁻¹ (9.95–24.51%), and 0.02–3.2 kg N ha⁻¹ (1.78–23.19%), respectively, compared to the winter fallow treatment. These results indicate that the combination of GM and a 40% reduction in N fertilizer can significantly reduce N runoff loss from paddy fields, demonstrating good effectiveness under various rainfall conditions, making it a green production model worth promoting. Full article

Rice is a staple food crop that feeds billions globally. Addressing Zn deficiency in rice is crucial for improving nutrition and food security. Zn deficiency in rice is a widespread issue, especially in purple tidal mud substrates, which often exhibit low Zn availability. The objective of this two-year pot study was to explore the relationship between Zn content, yield components, and Zn absorption in rice grown in purple tidal mud substrate with varying amounts of Chinese milk vetch (Astragalus sinicus L.) incorporation. The experimental design consisted of seven treatments: an unfertilized control, a Chinese milk vetch control, a chemical fertilizer control, and four treatment variations incorporating Chinese milk vetch alongside chemical fertilizer applications. The results indicated that planting and applying Chinese milk vetch improved the grain yield of rice in purple tidal mud substrate, and the yield increased with higher levels of Chinese milk vetch applied. The increased grain yield resulted in higher Zn absorption in rice grains. The application of Chinese milk vetch, both solely and in combination with chemical fertilizers, had varying effects on zinc uptake and grain zinc formation efficiency in early and late rice, with the control and low-level Chinese milk vetch treatments generally exhibiting the highest performance across the two-year period. By introducing Chinese milkvetch following the use of chemical fertilizers, the Zn content in rice grains increased starting from the second year. The treatment with Chinese milkvetch applied at a rate of 2.25 t/hm² showed the best results in increasing the Zn content in rice grains. The increase in Zn content and Zn uptake by the rice plants gave rise to a lowering of the DTPA-extractable Zn content in the purple tidal mud substrate. Sole Chinese milk vetch application and using Chinese milk vetch following chemical fertilizer application both increased Zn content extracted by DTPA in purple tidal mud substrate. Full article

Antimony (Sb) toxicity is a serious concern across the globe due to its hazardous impacts on plants and living organisms. The co-application of Chinese milk vetch (CMV) and biochar (BC) is a common agricultural practice, however, the effects of combined CMV and BC in mitigating Sb toxicity and bio-availability remain unclear. Therefore, this study investigated the impacts of CMV, rape straw biochar (RBC), and iron-modified biochar (FMB) and their combinations on rice productivity, physiological, and biochemical functioning of rice and Sb availability. Antimony toxicity caused a marked reduction in rice growth and productivity by decreasing chlorophyll, and anthocyanin synthesis, leaf water contents, osmolyte synthesis and antioxidant activities while, increasing hydrogen peroxide (H₂O₂), electrolyte leakage (EL), and malondialdehyde (MDA) production and Sb accumulation. Co-application of CMV and FMB increased biomass (29.50%) and grain yield (51.07%) of rice by increasing chlorophyll, and anthocyanin synthesis, leaf water contents, osmolyte synthesis, antioxidant activities, and decreasing production of H₂O₂, EL, and MDA and Sb accumulation in roots (90.41%) and shoots (96.38%). Furthermore, the combined addition of CMV and FMB also reduced the soil available Sb by 75.57% which resulted in less accumulation of Sb in plant parts and improved growth and yield. Given these facts, these findings indicate that co-application of CMV and FMB is a promising approach to remediate Sb-polluted soils and improve sustainable and safer rice productivity. Full article

In the traditional farming systems, the excessive application of chemical fertilizers to boost crop yields has resulted in a range of issues, such as soil quality degradation, soil structure deterioration, and pollution of the farmland ecological environment. Green manure, as a high-quality biological fertilizer source with rich nutrient content, is of great significance for enhancing the soil quality and establishing a healthy farmland ecosystem. However, there are few studies on the effects of different green manures on the soil nutrient levels, enzyme activities, and soil bacterial community composition in the rice–wheat rotation areas in southern China. Thus, we planted Chinese milk vetch (MV; Astragalus sinicus L.), light leaf vetch (LV; Vicia villosa var.), common vetch (CV; Vicia sativa L.), crimson clover (CC; Trifolium incarnatum L.), Italian ryegrass (RG; Lolium multiflorum L.), and winter fields without any crops as a control in the Taihu Lake area of Jiangsu. The soil samples collected after tilling and returning the green manure to the field during the bloom period were used to analyze the effects of the different green manures on the soil nutrient content, enzyme activity, and the structural composition of the bacterial community. This analysis was conducted using chemical methods and high-throughput sequencing technology. The results showed that the green manure returned to the field increased the soil pH, soil organic matter (SOM), alkali-hydrolyzed nitrogen (AN), available phosphorus (AP), available potassium (AK), sucrose (SC), urease (UE), and neutral phosphatase (NEP) contents compared to the control. They increased by 1.55% to 10.06%, 0.26% to 9.31%, 20.95% to 28.42%, 20.66% to 57.79%, 12.38% to 37.94%, 3.11% to 58.19%, 6.49% to 32.99%, and 50.0% to 80.36%, respectively. In addition, the green manure field increased the relative abundance of the genera Proteobacteria and Haliangium while decreasing the relative abundance of Gemmatimonadetes, Chloroflexi, SBR1031, and Anaeromyxobacter in the soil bacteria. Both the number of ASVs (amplicon sequence variants) and α-diversity of the soil bacterial communities were higher compared to the control, and the β-diversity varied significantly among the treatments. Alkali-hydrolyzed nitrogen and neutral phosphatase had the greatest influence on the soil bacterial community diversity, with alkali-hydrolyzed nitrogen being the primary soil factor affecting the soil bacterial community composition. Meanwhile, the results of the principal component analysis showed that the MV treatment had the most significant impact on soil improvement. Our study provides significant insights into the sustainable management of the soil quality in rice–wheat rotations. It identifies MV as the best choice among the green manure crops for improving the soil quality, offering innovative solutions for reducing chemical fertilizer dependence and promoting ecological sustainability. Full article

Milk vetch (Astragalus sinicus L.) is a winter-growing plant that can enhance soil fertility and provide essential nutrients for subsequent season crops. The fertilizing capacity of milk vetch is closely related to its above-ground biomass. Compared to the manual measurement methods of milk vetch biomass, remote sensing-based estimation methods have the advantages of rapid, noninvasive, and large-scale measurement. However, few studies have been conducted on remote sensing-based estimation of milk vetch biomass. To address this shortcoming, this study proposes combining unmanned aerial vehicle (UAV)-based hyperspectral imagery and machine learning algorithms for accurate estimation of milk vetch biomass. Through the analysis of hyperspectral images and feature selection based on the Pearson correlation and principal component analysis, vegetation indices (VIs), including near-infrared reflectance (NIR), red-edge spectral transform index (RE), and difference vegetation index (DVI), are selected as estimation metrics of the model development process. Four machine learning methods, including random forest (RF), multiple linear regression (MLR), deep neural network (DNN), and support vector machine (SVM), are used to construct the biomass models. The results show that the RF estimation model exhibits the highest coefficient of determination (R²) of 0.950 and the lowest relative root-mean-squared error (RRMSE) of 14.86% among all the models. Notably, the DNN model demonstrates promising performance on the test set, with the R² and RRMSE values slightly superior and inferior to those of the RF, respectively. The proposed method based on UAV imagery and machine learning can provide an accurate and reliable large-scale estimation of milk vetch biomass. Full article