System and method for the determination of produce shelf life

Abstract

A system and a method for the determination of product shelf life in a supply chain environment are discussed. The system receives periodic readings from various sensors that are associated with a shipment of produce. The system determines ambient deviations throughout the supply chain for temperature, humidity and ethylene. The system determines a product shelf life based on a calculated sensitivity and exposure to temperature, humidity, and ethylene. The system determines a remaining shelf life based on the determined product shelf life, and generates an event based on the remaining shelf life meeting a threshold. The system updates an indication of the remaining shelf life on a graphical interface for action.

Description

RELATED APPLICATIONS

This application claims priority to Indian Patent Application No. 201811009903 entitled “SYSTEM AND METHOD FOR THE DETERMINATION OF PRODUCE SHELF LIFE,” filed on Mar. 19, 2018, the content of which is hereby incorporated by reference in its entirety.

BACKGROUND

Supply chain systems monitor the movement of produce from an originating location through distribution channels to retail establishments.

BRIEF DESCRIPTION OF DRAWINGS

Illustrative embodiments are shown by way of example in the accompanying drawings and should not be considered as a limitation of the present disclosure:

FIG. 1 is a block diagram illustrating a system for the determination of product shelf life in a supply chain environment according to an exemplary embodiment.

FIG. 2 is a block diagram illustrating a system for the determination of product shelf life in a supply chain environment utilizing an unmanned aerial vehicle according to an exemplary embodiment.

FIG. 3 is a flow diagram illustrating a system for the determination of product shelf life in a supply chain environment according to an exemplary embodiment.

FIG. 4 depicts a block diagram of an exemplary computing device in accordance with an exemplary embodiment

DETAILED DESCRIPTION

Described in detail herein is a system and method that receive periodic readings from sensors distributed throughout the produce supply chain that detect ambient characteristics including temperature, humidity, and ethylene exposure. The system utilizes the sensor readings in conjunction with time exposure readings to determine a sensitivity of each type of produce to each of the characteristics. The sensitivity value may be applied along with subsequent readings to determine the remaining shelf life of a product within the supply chain. Shipments in the supply chain can be rerouted or accelerated based on remaining shelf life determination.

In another embodiment, the system receives periodic readings from sensors distributed on unmanned aerial vehicles. The periodic reading determines exposure to temperature, humidity and ethylene during portions of the produce's travel through the supply chain. For example, the unmanned aerial vehicles may take temperature, humidity and ethylene readings at a farm from which the produce originates its trip through the supply chain.

In one embodiment, periodic readings may be taken of the produce at various points in time during the produce's travel through the supply chain. The images may include images recorded from imaging sensors to determine physical characteristics of the produce at different points within the supply chain.

A number of terms used to explain embodiments of the present invention are now discussed. For example, as used herein “shelf life” is the length of time that a commodity may be stored without becoming unfit for use, consumption, or sale. In other words, shelf life might refer to whether a commodity should no longer be on a pantry shelf (unfit for use), or just no longer on a supermarket shelf (unfit for sale, but not yet unfit for use). For produce commodities, the shelf life may be the time a product may be stored without becoming unsuitable for use or consumption.

“Remaining shelf life” is a key performance indicator (KPI) that may predict the remaining life of a produce item at every node in a supply chain “Dynamic expiration” date may be the estimated expiration date that is calculated using the estimated remaining life of the item. Like the KPI, the dynamic expiration also changes with the change in ambient conditions. Elements in the supply chain that impact the shelf life of a perishable item include: time, temperature, humidity, damage, ethylene content, packaging, and other treatments/processing.

“Temperature sensitivities” of an item may be a measure of how susceptible a produce item is to a change in temperature. The sensitivity of an item is the measure of the reduction of life (in hours) of an item when there is unit degree change in temperature for an hour. Similarly, there are sensitivities related to humidity, ethylene content, packaging standards and treatment based sensitivities. Sensitivities may be computed by retaining samples of items from a load at the distribution center. The samples may require to be kept at different ambient conditions and may require to be monitored every day until expiration. The collected shelf life may then be regressed against the temperature to derive the sensitivities.

FIG. 1 is a block diagram illustrating a system for the determination of product shelf life in a supply chain environment according to an exemplary embodiment. The system 100 includes a shipment of product 116, a plurality of sensors distributed throughout the product supply chain including a temperature sensor 104, a humidity sensor 106, and an ethylene sensor 108. The sensors are connected through a network 114 to a server 102. Communicatively coupled, either locally or remotely, are one or more databases 112A, 112B for storing produce shelf life information. A reporting device 110 with a corresponding graphical user interface (GUI) 118 may be used to inform a user of the state of produce shelf life within the supply chain. The server 102 hosts the execution of the freshness indicator module 120 which determines the remaining shelf life of a shipment of produce and updates the GUI 118.

As described in this non-limiting embodiment, a shipment of produce 116 may be monitored by one or more sensors. As illustrated in FIG. 1, the shipment of produce 116 may be monitored by a temperature sensor 104, a humidity sensor 106, and an ethylene sensor 108. In other embodiments, a shipment of produce 116 may include a combination and varying numbers of sensors placed at varying proximities to the shipment of produce 116. In another embodiment, a combination of sensors may be integrated into a facility where the shipment of produce 116 is transiting. In another embodiment, a combination of sensors may be integrated into the transportation vehicle moving the shipment of produce 116 or a facility at which the produce is stored. In another embodiment, a combination of sensors may be integrated into the packaging, such as a pallet, of the produce during transport.

The sensors may take the form of embedded computing devices. An embodiment of the embedded computing device may be an Internet of Things (IoT) device. Advantages of IoT devices include the utilization of well known operational software packages, low power consumption, and a small footprint. Additionally IoT software stacks provide support for many alternative communication implementations. As discussed above in one embodiment, sensors are physical integrated into the containers that the produce transits the supply chain inside. In another embodiment, sensors may be more remote to the produce (e.g. integrated into the hold of a truck) but proximate enough to measure temperature, humidity and ethylene. Likewise IoT devices may be distributed throughout a distribution facility to provide the periodic readings necessary to determine remaining shelf life.

The sensors may communicate over a network 114. Utilizing an IoT software stack as described above, the plurality of sensors may utilize lower level network transport including but not limited to NB-IoT or LTE-Cat M1. Additionally non-IoT focused transport can be utilized for the connectivity of the sensors including WiFi, Bluetooth, and cellular LTE networks. The network 114 may include WANs, LANs, and the Internet. In the supply chain, the network 114 may include public or private portions of the internet, including utilizing virtualized private network (VPN) connections for data security.

The sensors provide periodic readings of data over the network 114 to a server 102. The server 102 receives periodic readings from the data across all sensors within the system. In one embodiment, the server 102 may be a dedicated physical computing device, or alternatively the server 102 may be a virtualized software server environment executing across a multiple computing devices.

Databases 112A, 112B catalog and index received periodic readings from the sensors. The databases 112A, 112B may be locally attached storage or area attached storage. The databases 112A, 112B may contain historical information utilized to identify characteristics of produce shipments indicative of various levels of remaining shelf life. The databases 112A, 112B may contain additional historical information utilized to train a machine learning algorithm, including a support vector machine, to characterize readings from the sensors as indicative of various states of remaining shelf life.

A reporting device 110 may be attached directly to the server 102, or more commonly, the reporting device 110 is communicatively attached through the network 114 to the server 102. In some embodiments, the reporting device 110 may be a mobile device such as a mobile phone or tablet. The reporting device 110 may include a display capable of rendering the graphical user interface (GUI) 118.

The GUI 118 may receive indications of remaining shelf life and display the remainders in an easy to read format. In some embodiments, the GUI 118 can display details regarding a shipment of produce and indicate a remaining time period corresponding to the remaining shelf life of the items in the shipment. It should be appreciated that a shipment may include one type of produce or multiple types of produce and each may have separate remaining shelf lives. Alternatively, the GUI 118 may provide a user with an indication to hold a shipment of produce based on the remaining shelf life. Holding a shipment of produce at a location may allow a user prevent a shipment of produce from proceeding to a location that may adversely affect the remaining shelf life so that the produce is unmarketable. The GUI 118 may provide a user an indication to reroute a shipment of produce based on the remaining shelf life. Based on current sensor readings at the current location of the shipment of produce, GUI 118 can display an indication that a shipment of produce is in jeopardy of exhausting its remaining shelf life, and prompt the user to relocate the shipment of produce where it can be sold while still viable.

Server 102 executes freshness indicator module 120. The freshness indicator module 120 evaluates the periodic readings from the sensors. The freshness indicator module 120 may require specific data to calculate the shelf life remaining. For example, in one embodiment, in a supply chain, the freshness indicator module 120 may require measurements for: supplier pick ambient temperatures (temperature at time of picking of the produce), supplier pack ambient temperature (temperature at time of packing of the produce), trailer ambient temperatures (temperature at time of shipping of the produce), distribution center ambient temperatures (temperature at time of intermediate storing of the produce) and a store ambient temperature (temperature at time of selling of the produce). Likewise for humidity, the freshness indicator module 120 may require: supplier pick ambient humidity, supplier pack ambient humidity, trailer ambient humidity, distribution center ambient humidity, and store ambient humidity. Similarly for ethylene readings, the freshness indicator module 120 may require: supplier pick ethylene, supplier pack ethylene, trailer ethylene, distribution center ethylene, and store ethylene.

Time intervals for the various periods for which the readings may occur may be determined for a number of different time periods occurring at a number of different phases during the transit of the produce through the supply chain. For example, time intervals may determined with reference to: pick date time, pack date time, cool date time, supplier ship date time, distribution receive date time, distribution center ship date time, store receive data time, store shelf replenishment data time, and store point of sale date time. Based on the date times collected throughout the supply chain, corresponding time intervals may be determined by subtracting combinations of the recorded dates. For example: Pick to cool/pack is the difference of the cool date time less the pick date time. Likewise, readings within the same phase (e.g. while produce is being stored at a distribution center) may also be used to determine how long produce was exposed to a particular temperature (or other types of readings).

“Ambient variations” as described herein are the differences between the ambient temperatures recorded at every point within the supply chain and a predetermined optimal/acceptable standard for that type of produce and reading. For example an ambient temperature variation is the difference of the measured ambient temperature less the standard temperature for the type of produce. Likewise ambient humidity variation is the difference of the measured ambient humidity less the standard humidity for the type of produce. For ethylene sensitive items, the ambient ethylene volume less the standard ethylene volume.

For calculating sensitivity, in one embodiment, retention sampling and other experimentation may be performed to arrive at the temperature, humidity and ethylene sensitivities of an item. At the farm or the distribution center, samples from harvest or shipments may be retained in various temperature and humidity zones and time to decay may be monitored for all the samples in order to get the life duration. After the experimentation; a regression may be used to arrive at the sensitivities expressed at:SL=(S_T*Temp)+(S_H*Humidity)+(S_E*Ethylene)+Error Valuewhere, S_T is the temperature sensitivity, S_H is the humidity sensitivity, S_E is the ethylene sensitivity, and SL is the shelf life of the items.

The remaining shelf life can be generated by the freshness indicator module at any point in the supply chain. In an embodiment, the freshness indicator module takes into account the time spent from harvest of the produce and the time/life lost (in hrs. or min.) due to changes in ambient temperature, humidity and ethylene content. The remaining shelf life may then be determined with the calculation expressed by:Product Shelf Life−((Produce Age)+(ΣS_T*Time of Temperature deviation*Temperature Deviation)+(ΣS_H*Time of Humidity deviation*Humidity Deviation)+(ΣS_E*Time of Ethylene deviation*Ethylene Deviation))

Upon the calculation of the remaining shelf life, the freshness indicator module 120 may update the GUI 118 over the network.

FIG. 2 is a block diagram illustrating a system 200 for the determination of product shelf life in a supply chain environment utilizing an unmanned aerial vehicle according to an exemplary embodiment. Similar to the system embodied in FIG. 1, the computational and reporting components (e.g. the server 102, the reporting device 110, and the network 114) maintain their described functionality. In FIG. 2, some of the sensors in the system are affixed to an unmanned aerial vehicle 202. Additionally, an imaging sensor 204 in the unmanned aerial vehicle 202 may augment the sensors array. In addition to the periodic readings taken corresponding to FIG. 1, the unmanned aerial vehicle 202 may include imaging of the origination of the supply chain. In one embodiment, the imaging may include that of supplier crops 206 in the field prior to and during harvest. Alternatively, the imaging may include harvested produce. This imaging may be supplemented with images not taken by the unmanned aerial vehicle 202, such as but not limited to images taken with a handheld imaging device, showing produce in cool rooms prior to shipping, produce in distribution centers and produce in store. The images may be transmitted back to the freshness indicator module 120. The freshness indicator module 120 may process the imaging by identifying a set of characteristics present in the imaging indicative of remaining shelf life. For example, color changes of produce may be a characteristic indicative of remaining shelf life. Other defects of produce, such as skin reflectivity, may be characteristics indicative of remaining shelf life. The freshness indicator module 120 compares the set of characteristics extracted from the imaging and compares them to a set of known control characteristics. The known control characteristics may be determined through experimentation and stored in the databases 112A, 112B (e.g. as a library of images). Based on the comparison, the freshness indicator module 120 may correlate a remaining shelf life of the produce from the control. Additionally, the characteristic comparison may be utilized in conjunction with the measurements and calculations as described regarding FIG. 1 to provide better accuracy in predicting remaining shelf life. The combination of both approaches may also provide training inputs for a machine learning algorithm for additional confidence.

FIG. 3 is a flow diagram illustrating a system for the determination of product shelf life in a supply chain environment according to an exemplary embodiment.

At step 302, the freshness indicator module receives periodic readings associated with a shipment of produce from sensors distributed at locations throughout a produce supply chain. The locations may include an initial location at which the produce originated. Additional locations may include the transportation vehicles, distribution centers, and stores.

At step 304, the freshness indicator module determines ambient deviations throughout the supply chain for temperature, humidity and ethylene. Pre-defined criteria for the shipment of produce may be based at least in part on the periodic readings and utilized to build confidence in the remaining shelf life determinations.

At step 306, the freshness indicator module determines a product shelf life based on a calculated sensitivity to temperature in conjunction with an amount of time of temperature deviation and an amount of temperature deviation, a calculated sensitivity to humidity in conjunction with an amount of time of humidity deviation and an amount of humidity deviation, and calculated sensitivity to ethylene in conjunction with an amount of time of ethylene deviation and an amount of ethylene deviation. The freshness indicator module may calculate a sensitivity to temperature, a sensitivity to humidity, and a sensitivity to ethylene for the shipment of produce based at least in part on the periodic readings.

The calculation of a sensitivity to temperature, a sensitivity to humidity, and a sensitivity to ethylene for the shipment of produce may be calculated using machine learning to periodically recalculate sensitivity based on additional readings received from the sensors. Training and periodic validation of the machine learning algorithm may be utilized to provide data points in a supervised learning activity.

At step 308, the freshness indicator module determines a remaining shelf life based on the determined product shelf life, an age of the shipment of produce, and conditions of the shipment of product in transit, the remaining shelf life representing a time period the shipment of produce is fit for sale.

At step 310, freshness indicator module generates an event based on the remaining shelf life meeting a threshold. A first threshold may correspond to the produce becoming unfit for sale. In one embodiment, the freshness indicator module may automatically divert the shipment of produce to another location based on the event. Alternatively, the freshness indicator module may automatically hold the shipment of product at one location based on the event. Additionally, the freshness indicator module may generate a second event based on the remaining life meeting a second threshold. The second threshold may indicate that the produce is unfit for consumption. The freshness indicator may update an indication on a graphical user interface corresponding to the second event, indicating the shipment of produce has no remaining shelf life and is unfit for consumption.

At step 312, the freshness indicator module updates an indication of the remaining shelf life on a graphical user interface. The update can include a number of actions a user may take based on the remaining shelf life. For example, if the remaining shelf life is no longer fit for sale, the user may be presented with an option to generate orders to discard the shipment.

FIG. 4 is a block diagram of an example computing device for implementing exemplary embodiments of the present disclosure. Embodiments of the computing device 400 can implement embodiments of the system for the determination of product shelf life in a supply chain environment. For example, the computing device can be embodied as a portion of the server 102, sensors 104, 106, 108, 204, and reporting devices 110. The computing device 400 includes one or more non-transitory computer-readable media for storing one or more computer-executable instructions or software for implementing exemplary embodiments. The non-transitory computer-readable media may include, but are not limited to, one or more types of hardware memory, non-transitory tangible media (for example, one or more magnetic storage disks, one or more optical disks, one or more flash drives, one or more solid state disks), and the like. For example, memory 406 included in the computing device 400 may store computer-readable and computer-executable instructions or software (e.g., the GUI 118) for implementing exemplary operations of the computing device 400. The computing device 400 also includes configurable and/or programmable processor 402 and associated core(s) 404, and optionally, one or more additional configurable and/or programmable processor(s) 402′ and associated core(s) 404′ (for example, in the case of computer systems having multiple processors/cores), for executing computer-readable and computer-executable instructions or software stored in the memory 406 and other programs for implementing exemplary embodiments of the present disclosure. Processor 402 and processor(s) 402′ may each be a single core processor or multiple core (404 and 404′) processor. Either or both of processor 402 and processor(s) 402′ may be configured to execute one or more of the instructions described in connection with computing device 400.

Virtualization may be employed in the computing device 400 so that infrastructure and resources in the computing device 400 may be shared dynamically. A virtual machine 412 may be provided to handle a process running on multiple processors so that the process appears to be using only one computing resource rather than multiple computing resources. Multiple virtual machines may also be used with one processor.

Memory 406 may include a computer system memory or random access memory, such as DRAM, SRAM, EDO RAM, and the like. Memory 406 may include other types of memory as well, or combinations thereof. The computing device 400 can receive data from input/output devices. A user may interact with the computing device 400 through a visual display device 414, such as a computer monitor, which may display one or more graphical user interfaces 416, multi touch interface 420 and a sensor input 418 corresponding to the sensor 104, 106, 108, 204 being employed.

The computing device 400 may also include one or more storage devices 426, such as a hard-drive, CD-ROM, or other computer readable media, for storing data and computer-readable instructions and/or software that implement exemplary embodiments of the present disclosure (e.g., GUI 118). For example, exemplary storage device 426 can include one or more databases 428 for storing information associated sensor reading and data related to product shelf life. The databases 428 may be updated manually or automatically at any suitable time to add, delete, and/or update one or more data items in the databases.

The computing device 400 can include a network interface 408 configured to interface via one or more network devices 424 with one or more networks, for example, Local Area Network (LAN), Wide Area Network (WAN) or the Internet through a variety of connections including, but not limited to, standard telephone lines, LAN or WAN links (for example, 802.11, T1, T3, 56 kb, X.25), broadband connections (for example, ISDN, Frame Relay, ATM), wireless connections, controller area network (CAN), or some combination of any or all of the above. In exemplary embodiments, the computing system can include one or more antennas 422 to facilitate wireless communication (e.g., via the network interface) between the computing device 400 and a network and/or between the computing device 400 and other computing devices. The network interface 408 may include a built-in network adapter, network interface card, PCMCIA network card, card bus network adapter, wireless network adapter, USB network adapter, modem or any other device suitable for interfacing the computing device 400 to any type of network capable of communication and performing the operations described herein.

The computing device 400 may run any operating system 410, such as any of the versions of the Microsoft® Windows® operating systems, the different releases of the Unix and Linux operating systems, any version of the MacOS® for Macintosh computers, any embedded operating system, any real-time operating system, any open source operating system, any proprietary operating system, or any other operating system capable of running on the computing device 400 and performing the operations described herein. In exemplary embodiments, the operating system 410 may be run in native mode or emulated mode. In an exemplary embodiment, the operating system 410 may be run on one or more cloud machine instances.

In describing exemplary embodiments, specific terminology is used for the sake of clarity. For purposes of description, each specific term is intended to at least include all technical and functional equivalents that operate in a similar manner to accomplish a similar purpose. Additionally, in some instances where a particular exemplary embodiment includes multiple system elements, device components or method steps, those elements, components, or steps can be replaced with a single element, component, or step. Likewise, a single element, component, or step can be replaced with multiple elements, components, or steps that serve the same purpose. Moreover, while exemplary embodiments have been shown and described with references to particular embodiments thereof, those of ordinary skill in the art will understand that various substitutions and alterations in form and detail can be made therein without departing from the scope of the present disclosure. Further, still, other aspects, functions, and advantages are also within the scope of the present disclosure.

Exemplary flowcharts are provided herein for illustrative purposes and are non-limiting examples of methods. One of ordinary skill in the art will recognize that exemplary methods can include more or fewer steps than those illustrated in the exemplary flowcharts and that the steps in the exemplary flowcharts can be performed in a different order than the order shown in the illustrative flowcharts.

Claims

1. A system for determining a shelf life of produce within a supply chain comprising: a plurality of sensors distributed at a plurality of locations throughout a produce supply chain, the plurality of locations including an initial location at which the produce originated;an imaging sensor, wherein the imaging sensor is configured to capture images of the produce;a computing device communicatively coupled to the plurality of sensors and configured to execute a freshness indicator module, the freshness indicator module when executed: receiving periodic readings from the plurality of sensors associated with a shipment of produce,determining ambient deviations throughout the supply chain for temperature, humidity and ethylene from pre-defined criteria for the shipment of produce based at least in part on the periodic readings,calculating a sensitivity to temperature, a sensitivity to humidity, and a sensitivity to ethylene for the shipment of produce based at least in part on the periodic readings, wherein the calculation of the sensitivity to temperature, the sensitivity to humidity, and the sensitivity to ethylene for the shipment of produce is calculated using machine learning to periodically recalculate sensitivity based on additional readings received from the plurality of sensors,determining a product shelf life based on the calculated sensitivity to temperature in conjunction with an amount of time of temperature deviation and an amount of temperature deviation, the calculated sensitivity to humidity in conjunction with an amount of time of humidity deviation and an amount of humidity deviation, and the calculated sensitivity to ethylene in conjunction with an amount of time of ethylene deviation and an amount of ethylene deviation,capturing, via the imaging sensor, an image of the shipment of produce,determining a first set of characteristics within the image of the shipment of produce,comparing the first set of characteristics against a second set of characteristics consistent with a known condition of a control shipment of the produce,determining a remaining shelf life based on the determined product shelf life, an age of the shipment of produce, conditions of the shipment of product in transit, and the comparison of the first set of characteristics against the second set of characteristics, the remaining shelf life representing a time period the shipment of produce is fit for sale,generating an event based on the remaining shelf life meeting a threshold, andupdating an indication of the remaining shelf life on a graphical user interface.

2. The system of claim 1, wherein the plurality of sensors include temperature sensors, humidity sensors, and ethylene sensors and are affixed to an unmanned aerial vehicle.

3. The system of claim 1, wherein the product shelf life is calculated using the equation: SL=(ST*Temp)+(SH*Humidity)+(SE*Ethylene)+Error Value.

4. The system of claim 1, wherein the remaining life is calculated using the equation: Product Shelf Life−((Produce Age)+(ΣST*Time of Temperature deviation*Temperature Deviation)+(ΣSH*Time of Humidity deviation*Humidity Deviation)+(ΣSE*Time of Ethylene deviation*Ethylene Deviation)).

5. The system of claim 1, the freshness indicator module when executed further: generates a second event based on the remaining life traversing a second threshold, and updates an indication on a graphical user interface corresponding to the second event, wherein the indication represents the remaining life corresponds to the shipment of produce being unfit for consumption.

6. A method for determining shelf life of produce within a supply chain comprising: receiving periodic readings associated with a shipment of produce from a plurality of sensors distributed at a plurality of locations throughout a produce supply chain, the plurality of locations including an initial location at which the produce originated;determining ambient deviations throughout the supply chain for temperature, humidity and ethylene from pre-defined criteria for the shipment of produce based at least in part on the periodic readings;calculating a sensitivity to temperature, a sensitivity to humidity, and a sensitivity to ethylene for the shipment of produce based at least in part on the periodic readings, wherein the calculation of the sensitivity to temperature, the sensitivity to humidity, and the sensitivity to ethylene for the shipment of produce is calculated using machine learning to periodically recalculate sensitivity based on additional readings received from the plurality of sensors;determining a product shelf life based on the calculated sensitivity to temperature in conjunction with an amount of time of temperature deviation and an amount of temperature deviation, the calculated sensitivity to humidity in conjunction with an amount of time of humidity deviation and an amount of humidity deviation, and the calculated sensitivity to ethylene in conjunction with an amount of time of ethylene deviation and an amount of ethylene deviation;capturing, via an imaging sensor, an image of the shipment of produce;determining a first set of characteristics within the image of the shipment of produce;comparing the first set of characteristics against a second set of characteristics consistent with a known condition of a control shipment of the produce;determining a remaining shelf life based on the determined product shelf life, an age of the shipment of produce, conditions of the shipment of product in transit, and the comparison of the first set of characteristics against the second set of characteristics, the remaining shelf life representing a time period the shipment of produce is fit for sale;generating an event based on the remaining shelf life meeting a threshold; andupdating an indication of the remaining shelf life on a graphical user interface.

7. The method of claim 6, further comprising: diverting the shipment of produce to another location or holding the shipment of produce at one location based on the event.

8. The method of claim 6, wherein the product shelf life is calculated using the equation: SL=(ST*Temp)+(SH*Humidity)+(SE*Ethylene)+Error Value.

9. The method of claim 6, wherein the remaining life is calculated using the equation: Product Shelf Life−((Produce Age)+(ΣST*Time of Temperature deviation*Temperature Deviation)+(ΣSH*Time of Humidity deviation*Humidity Deviation)+(ΣSE*Time of Ethylene deviation*Ethylene Deviation)).

10. The method of claim 6, further comprising: generating a second event based on the remaining life traversing a second threshold, andupdating an indication on a graphical user interface corresponding to the second event, wherein the indication represents the remaining life corresponds to the shipment of produce being unfit for consumption.

11. A non-transitory computer readable medium holding instructions for determining shelf life of produce within a supply chain, the instructions when executed by a processor causing at least one computing device to: receive periodic readings associated with a shipment of produce from a plurality of sensors distributed at a plurality of locations throughout a produce supply chain, the plurality of locations including an initial location at which the produce originated;determine ambient deviations throughout the supply chain for temperature, humidity and ethylene from pre-defined criteria for the shipment of produce based at least in part on the periodic readings;calculate a sensitivity to temperature, a sensitivity to humidity, and a sensitivity to ethylene for the shipment of produce based at least in part on the periodic readings, wherein the calculation of the sensitivity to temperature, the sensitivity to humidity, and the sensitivity to ethylene for the shipment of produce is calculated using machine learning to periodically recalculate sensitivity based on additional readings received from the plurality of sensors;determine a product shelf life based on the calculated sensitivity to temperature in conjunction with an amount of time of temperature deviation and an amount of temperature deviation, the calculated sensitivity to humidity in conjunction with an amount of time of humidity deviation and an amount of humidity deviation, and the calculated sensitivity to ethylene in conjunction with an amount of time of ethylene deviation and an amount of ethylene deviation,capture, via an imaging sensor, an image of the shipment of produce;determine a first set of characteristics within the image of the shipment of produce;compare the first set of characteristics against a second set of characteristics consistent with a known condition of a control shipment of the produce;determine a remaining shelf life based on the determined product shelf life, an age of the shipment of produce, conditions of the shipment of product in transit, and the comparison of the first set of characteristics against the second set of characteristics, the remaining shelf life representing a time period the shipment of produce is fit for sale;generate an event based on the remaining shelf life meeting a threshold; andupdate an indication of the remaining shelf life on a graphical user interface.

12. The medium of claim 11, wherein the product shelf life is calculated using the equation: (ST*Temp)+(SH*Humidity)+(SE*Ethylene)+Error.

13. The medium of claim 11, wherein the remaining life is calculated using the equation: Product Shelf Life−((Produce Age)+(ΣST*Time of Temperature deviation*Temperature Deviation)+(ΣSH*Time of Humidity deviation*Humidity Deviation)+(ΣSE*Time of Ethylene deviation*Ethylene Deviation)).