China Requires a Sustainable Transition of Vegetable Supply from Area-Dependent to Yield-Dependent and Decreased Vegetable Loss and Waste

Evaluation of two deep learning-based approaches for detecting weeds growing in cabbage

BACKGROUND

Machine vision-based precision weed management is a promising solution to substantially reduce herbicide input and weed control cost. The objective of this research was to compare two different deep learning-based approaches for detecting weeds in cabbage: (1) detecting weeds directly, and (2) detecting crops by generating the bounding boxes covering the crops and any green pixels outside the bounding boxes were deemed as weeds.

RESULTS

The precision, recall, F1-score, mAP0.5, mAP0.5:0.95 of You Only Look Once (YOLO) v5 for detecting cabbage were 0.986, 0.979, 0.982, 0.995, and 0.851, respectively, while these metrics were 0.973, 0.985, 0.979, 0.993, and 0.906 for YOLOv8, respectively. However, none of these metrics exceeded 0.891 when detecting weeds. The reduced performances for directly detecting weeds could be attributed to the diverse weed species at varying densities and growth stages with different plant morphologies. A segmentation procedure demonstrated its effectiveness for extracting weeds outside the bounding boxes covering the crops, and thereby realizing effective indirect weed detection.

CONCLUSION

The indirect weed detection approach demands less manpower as the need for constructing a large training dataset containing a variety of weed species is unnecessary. However, in a certain case, weeds are likely to remain undetected due to their growth in close proximity with crops and being situated within the predicted bounding boxes that encompass the crops. The models generated in this research can be used in conjunction with the machine vision subsystem of a smart sprayer or mechanical weeder. © 2024 Society of Chemical Industry.

Determining optimal range of reduction rates for nitrogen fertilization based on responses of vegetable yield and nitrogen losses to reduced nitrogen fertilizer application

Vegetable production is commonly accompanied by high nitrogen fertilizer rates but low nitrogen use efficiency in China. Reduced fertilization has been frequently recommended in existing studies as an efficient measurement to avoid large amount of nutrient loss and subsequent nonpoint source pollution. However, the reported responses of vegetable yield and nitrogen losses to reduced fertilization rates varied in a large range, which has resulted into large uncertainties in the potential benefits of those recommended reduction rates. Thus, we constructed the relationship between responses of nitrogen losses and vegetable yield to reduced nitrogen fertilization rates to determine the optimal range of reduction rates for nitrogen fertilization in a proportional form based on data reported in literatures across China's mainland, and evaluated the roles of greenhouse, managing options, and vegetable species on the responses. The relationships were constructed separately for 4 subregions: Northern arid and semiarid, loess plateau regions (NSL), Temperate monsoon zone (TMZ), Southeast monsoon zone (SMZ), Southwest zone (SWZ). The optimal nitrogen fertilizer reduction range for the TMZ, SMZ and SWZ were 51 % to 67 %, 40 % to 66 % and 54 % to 80 %, respectively and no reduction for NSL. Vegetable yields were not be sacrificed when fertilizations were reduced within the optimal ranges. Greenhouse and managing options showed no significant effect on the responses of both vegetable yield and nitrogen losses by the optimal reduction range but vegetable species played a relatively important role on the responses of vegetable yield. This indicated that the optimal reduction rates can be effective on reducing nitrogen loss in both open-field and greenhouse conditions across China's mainland without extra managing options. Therefore, the optimal reduction rates can still serve as a good starting point for making regional plans of nitrogen reduction that help balancing the chasing of high vegetable yield and low nitrogen loss.

New vegetable field converted from rice paddy increases net economic benefits at the expense of enhanced carbon and nitrogen footprints

China accounts for around 50 % of the global vegetable harvested area which is expected to increase continuously. Large cropland areas, including rice paddy, have been converted into vegetable cultivation to feed an increasingly affluent population and increase farmers' incomes. However, little information is available on the balance between economic benefits and environmental impacts upon rice paddy conversion into vegetable fields, especially during the initial conversion period. Herein, the life cycle assessment approach was applied to compare the differences in agricultural input costs, yield incomes, net economic benefits (NEB), carbon (C) and nitrogen (N) footprints and net ecosystem economic benefits (NEEB) between the double rice paddy (Rice) and newly vegetable field (Veg) converted from Rice based on a four-year field experiment. Results showed that yield incomes from Veg increased by 96-135 %, outweighing the increased agricultural input costs due to higher inputs of labor and pesticide, thus significantly increasing NEB by 80-137 %, as compared to Rice. Rice conversion into Veg largely increased C footprints by 2.3-10 folds and N footprints by 1.1-2.6 folds, consequently increasing the environmental damage costs (EDC) by 2.2 folds on average. The magnitudes of increases in C and N footprints and EDC due to conversion strongly declined over time. The NEEB, the trade-offs between NEB and EDC, decreased by 18 % in the first year, while increasing by 63 % in the second year and further to 135 % in the fourth year upon conversion. These results suggested that rice paddy conversion into vegetable cultivation could increase the NEB at the expense of enhanced EDC, particular during the initial conversion years. Overall, these findings highlight the importance of introducing interventions to mitigate C and N footprints from newly converted vegetable field, so as to maximize NEEB and realize the green and sustainable vegetable production.

Contrasting fertilization response of soil phosphorus forms and functional bacteria in two newly reclaimed vegetable soils

Fertilization is a pervasive approach to agricultural production enhancing vegetable nutrients such as phosphorus (P) absorption. However, unreasonable fertilization strategies result in high levels of residual P in vegetable planting systems. To better understand the mechanisms of soil phosphorus dynamics responding to inorganic/organic fertilization, we conducted a 3-year field experiment in two newly reclaimed vegetable fields in southern China. The results revealed that soil Olsen-P in CF (mineral fertilization) and OF (Combined application of organic and inorganic fertilizers) increased by approximately 210.6 % and 183.6 %, respectively, while stable P proportion decreased by approximately 9.2 % and 18.1 %, respectively, compared with CK. Combined application of organic and inorganic fertilizer increased the proportion of moderately labile P (NaOH-P) by 1-6 % in comparison with chemical fertilizer and facilitated the conversion from diester-P to monoester-P, indicating that applying pig manure enhanced the potential soil P bioavailability. Besides, organic-inorganic fertilization shaped a bacterial community with more connectivity and stability and changed keystone taxa related to the P transformation of the network. Phenylobacterium, Solirubrobacter, and Modestobacter were regarded as core genera for mobilizing soil phosphorus. However, residual P content in newly reclaimed soils under fertilization, especially for chemical fertilizer, remained non-negligible and may cause potential environmental risks. The partial least squares path modeling results demonstrated that fertilization management had both direct and indirect positive effects on P fraction through the improvement of soil nutrients e.g. total N and soil organic carbon, and bacterial community, while soil properties mainly determined the variation of soil P species. Our results provide comprehensive insights into the current status of legacy P forms and the vital role of fertilizer, key soil properties and bacteria in P dynamics in newly reclaimed vegetable field.

Recent preparation, modification and application progress of starch nanocrystals: A review

Due to the advantages of wide sources, high biocompatibility and favorable biodegradability, starch nanocrystals (SNCs) have gradually attracted attention and have bright development prospects in food, agriculture, materials, medicine and other fields. However, the traditional preparation method of SNCs is time-consuming and inefficient, and the physicochemical properties cannot fully meet the needs of multiple applications. Fortunately, the unique onion-like structure of starch granules and the large number of hydroxyl groups present on the surface entitle SNCs to efficient preparation and modification. This paper comprehensively reviewed the improvement methods of SNCs preparation process in recent years, and the advantages and disadvantages of the two improvement strategies were compared. Besides, the importance of introducing different pretreatment methods into the SNCs preparation process was emphasized. It also focused on the different modification treatment and application progress of SNCs, especially in the starch-based surface coating of fruits and vegetables. The information will contribute to further improve the preparation efficiency and physicochemical properties of SNCs, and ultimately expand the application field.